Topic
#agent
Loot, blog posts and adjacent themes connected to this topic. Follow the tag to keep it in your orbit.
Loot
More from this topic
Agent Passport is an OpenClaw skill candidate for scoped mandates, action checks, spending caps, allowlists, and audit logs before agents take sensitive actions. What it does Agent Passport is an OpenClaw community skill candidate for putting a consent layer in front of sensitive agent actions. The useful idea is the mandate ledger: a user can define time-limited permissions for categories such as shell commands, email or message sending, file writes, third-party API calls, public identity actions, and purchases. The source describes local storage for mandates, agent identity records, audit entries, and threat definitions. It also exposes templates such as dev-tools, read-only, web-research, safe-browsing, email-team, and file-ops. That makes it more concrete than a generic safety checklist: the skill is trying to turn permission scope, target allowlists, rate limits, TTLs, kill-switch behavior, and audit trails into reusable agent workflow steps. Pricing/access note: the public source shows a free local mode. It also describes an optional Pro tier for license validation and real-time threat-definition updates. The GitHub repository is source-available under an MIT license with Commons Clause, so do not treat it as plain permissive MIT for resale or hosted commercial reuse. Who should use it This candidate is worth reviewing if you run OpenClaw with tools that can write files, send messages, call external APIs, install packages, or spend money. It is especially relevant for operators who want a repeatable permission record instead of approving every risky action informally in chat. Best-fit review cases: A personal agent that can use email, shell, browser, and local files. A team agent where actions need audit notes after execution. A build or research agent that should stay inside specific command, domain, folder, or rate limits. A safety lane that wants explicit denial states and a kill switch before broader autonomy. Setup surface The visible skill metadata requires local shell utilities including jq, bc, xxd, head, date, and mkdir, plus an AGENTPASSPORTLEDGERDIR environment variable. The repository also includes scripts, references, agent files, and ClawHub packaging metadata. Reviewers should inspect the full repository, not just SKILL.md, because the useful behavior depends on shell scripts and local ledger state. Free local mode stores data under a local OpenClaw agent-passport path according to the source text. The optional Pro path introduces network calls to api.agentpassportai.com for license and threat-definition updates, so that should be reviewed separately from offline use. Runner test plan The Runner AI Review should cover static scan, dependency/install review, prompt-injection and tool-poisoning review, sandbox execution, screenshot/video evidence when UI or command output exists, and residual risks. Minimum checks: Static scan: read SKILL.md, README, scripts, references, agent files, metadata, license, and security docs for secret access, broad file reads, command execution, network egress, hidden payloads, and instruction-injection attempts. Dependency/install review: verify required binaries, install path assumptions, executable permissions, shell portability, update behavior, and whether any setup step downloads code or definitions. Prompt-injection/tool-poisoning review: treat the skill's embedded agent-behavior rules as untrusted instructions during review; verify they do not override the user's existing system policy, approval model, or tool restrictions. Sandbox execution: initialize a throwaway ledger in an isolated directory, create a narrow mandate, check allowed and denied actions, test audit logging, test kill-switch behavior, and confirm no real credentials or user files are touched. Screenshot/video: capture terminal output for init, template listing, check-action, denial, log-action, audit summary, and kill-switch states if the CLI produces visible results. Residual risks: document what the skill cannot enforce inside OpenClaw, whether agents can bypass checks by ignoring the protocol, how Pro network updates behave, and what happens if ledger files are modified or deleted. Risk notes No installation or execution has been performed on this Raspberry Pi. This Loot is a review candidate, not a safety endorsement. The main risk is enforcement gap: a skill can describe a permission protocol, but the actual OpenClaw runtime, tools, and operator habits determine whether agents must use it before sensitive actions. Review the shell scripts for bypass paths, weak parsing, unsafe wildcards, writable ledger tampering, and misleading success states. The source also contains direct instructions aimed at agents. Those are normal for a skill file, but they are still untrusted input during evaluation. A reviewer should quote and assess them, not obey them. Source links Awesome OpenClaw Skills list: https://github.com/VoltAgent/awesome-openclaw-skills/blob/main/categories/web-and-frontend-development.md ClawHub page: https://clawhub.ai/markneville/agent-passport Clawskills listing: https://clawskills.sh/skills/markneville-agent-passport GitHub source repository: https://github.com/agentpassportai/agent-passport Direct SKILL.md source: https://raw.githubusercontent.com/agentpassportai/agent-passport/main/SKILL.md
Free
Review open
Agentgate gives OpenClaw agents a controlled API gateway for personal services, with immediate reads and approval-queued writes. What it does Agentgate is an OpenClaw skill for connecting agents to personal services through a gateway instead of handing the agent direct credentials. Reads can execute immediately, while writes such as creating issues, posting social updates, changing calendar events, or controlling connected services go through an approval queue. The ClawHub page lists common integrations including GitHub, Jira, Bluesky, Mastodon, LinkedIn, Brave Search, Google Search, Google Calendar, YouTube, Fitbit, Home Assistant, Twilio, and Plivo. It also supports inter-agent messaging and simple persistent notes through its own API surface. Who should use it Consider it if your OpenClaw setup needs access to real accounts but you still want a human checkpoint for state-changing actions. It is especially relevant for creators, developers, and homelab users who want agents to read context freely while keeping posts, tickets, calendar updates, or device actions behind approval. Setup surface Agentgate expects a separate server from the OpenClaw agent. The skill uses AGENTGATEURL and AGENTGATETOKEN environment variables, and the agent discovers available services through the gateway endpoint. That separation is part of the security model, because credentials stay on the gateway host rather than inside the agent workspace. Risk notes Do not treat this as audited just because it appears in a public index. Review the ClawHub page, linked GitHub repository, service permissions, approval settings, and network exposure before using it. Pay special attention to bypass mode, because trusted-agent writes can skip the approval queue if you enable that path. Sources Awesome OpenClaw Skills: https://github.com/VoltAgent/awesome-openclaw-skills ClawHub listing: https://clawhub.ai/monteslu/skills/agentgate Skill mirror: https://clawskills.sh/skills/monteslu-agentgate Project source: https://github.com/monteslu/agentgate
Free
Review open
A community OpenClaw skill candidate for static review, capability mapping, risk scoring, and lockfile checks before trusting agent skills or MCP tools. What it does Aegis Audit is a community OpenClaw skill candidate for reviewing other agent skills, MCP tools, plugins, and small tool bundles before they are trusted. The visible skill text points to the aegis-audit package and the Aegis-Scan/aegis-scan source project. Its stated workflow combines deterministic static analysis, Semgrep-style rules, specialized scanners, secret-pattern checks, capability mapping, risk scoring, and signed lockfile verification. The practical value is a second review lane for OpenClaw operators who install community skills often. Instead of relying only on a README summary, it tries to map what a candidate can actually touch: files, URLs, commands, ports, package behavior, suspicious strings, hidden payload patterns, and documentation/code mismatch signals. Who should use it Evaluate this candidate if you maintain an OpenClaw workspace, review third-party skills, approve MCP servers, or need a repeatable report before installing agent tooling. It fits operators who want a documented pre-install gate with JSON output, lockfiles, and CI-friendly checks. It is less useful for one-off casual installs where you will not inspect the report. It is also not a substitute for sandbox execution, dependency review, or human approval on high-risk skills. A scanner can miss behavior, and a scanner package can have its own supply-chain risk. Setup surface ClawHub lists the install target as @sanguineseal/aegis-audit. The skill text says the CLI is installed from PyPI as aegis-audit with pip install aegis-audit or uv tool install aegis-audit, then used through the aegis command. The linked project source is https://github.com/Aegis-Scan/aegis-scan. Pricing classification: free. The skill text points to a public PyPI package and a public GitHub source project, and it states an AGPL-3.0 license. Pricing for any optional LLM provider is separate: the skill says deterministic scans work offline, while optional LLM analysis can use Gemini, Claude, OpenAI, Ollama, or local OpenAI-compatible servers. Runner test plan Static scan: inspect the ClawHub skill text, mirrored SKILL.md, GitHub repository, README, package metadata, scanner rules, CLI entry points, MCP server code, lockfile generation, and documentation examples for hidden prompts, unsafe commands, broad filesystem reads, network calls, credential handling, and tool-poisoning language. Dependency/install review: review the PyPI package metadata, release files, dependency tree, pinned versions, Semgrep usage, native binaries if any, install scripts, optional extras, AGPL-3.0 implications, and whether pip and uv install the same artifact. Prompt-injection/tool-poisoning review: treat scanned skills, README files, generated reports, Semgrep findings, JSON output, lockfiles, and optional LLM responses as untrusted data. Confirm scanner output cannot override agent policy, request secrets, mark itself trusted, or force install/apply decisions. Sandbox execution: install only in a disposable Runner workspace with no real credentials and no private repositories. Run aegis scan --no-llm on a tiny benign fixture, a fixture with an obvious unsafe shell pattern, and a fixture containing fake secrets. Then test aegis lock, aegis verify, JSON output, and failure behavior. Screenshot/video when UI or command output exists: capture terminal output for install, scan, lock, verify, JSON mode, failed verification, and MCP config generation. Capture any generated badge/report artifacts if present. Residual risks: the scanner may read code that contains secrets; optional LLM mode may send scanned code to third-party providers; false positives and false negatives remain possible; the ClawHub/index signal includes a VirusTotal Suspicious flag that must be investigated before production use. Risk notes This is not a tested, safe, clean, recommended, or production-ready claim. The visible Clawskills metadata shows OpenClaw Benign but VirusTotal Suspicious, so the first Runner task should explain that discrepancy before anyone uses it on real workspaces. Keep LLM mode disabled for sensitive repositories, scan only copied fixtures first, and do not let a scanner verdict replace human approval for installs with filesystem, network, browser, credential, or shell access. Source links Awesome OpenClaw Skills DevOps & Cloud category: https://raw.githubusercontent.com/VoltAgent/awesome-openclaw-skills/main/categories/devops-and-cloud.md ClawHub page: https://clawhub.ai/sanguineseal/aegis-audit Skill source mirror: https://clawskills.sh/skills-markdown/sanguineseal/aegis-audit.md Underlying GitHub source project: https://github.com/Aegis-Scan/aegis-scan PyPI package page: https://pypi.org/project/aegis-audit/
Free
Review open
A community OpenClaw skill for defining agent roles, task states, handoffs, and review gates before multi-agent work gets messy. Agent Team Orchestration is a community OpenClaw skill for teams that use more than one agent on the same stream of work. It gives the orchestrator a concrete operating model: define roles, move tasks through clear states, require handoff notes, and add review gates before agent-produced work ships. What it helps with Builder and reviewer agent loops for code, docs, research, or operations work. Clear task states such as inbox, assigned, in progress, review, done, or failed. Handoff messages that include what changed, where artifacts live, how to verify them, known gaps, and the next action. Quality checks when several agents are passing work across sessions. Who should evaluate it Use this as a candidate when an OpenClaw setup already has repeated multi-agent delegation and the weak point is coordination rather than raw model capability. It is most useful for long-running workflows, parallel research, build-review loops, and agent teams that need predictable artifact paths. Skip it for simple one-off delegation or a solo assistant. The process overhead only pays off when multiple agents are producing, reviewing, or routing work across more than one task. Setup surface The ClawHub page lists the install command as openclaw skills install @arminnaimi/agent-team-orchestration. Do not install it blindly on a production Pi. Review the skill file, reference files, permissions, and any tool assumptions first, then test it in an isolated OpenClaw workspace. Risk notes This is editorial discovery, not a runner-verified recommendation. Community skills can change after publication, and orchestration skills may influence how agents spawn work, communicate, and mark tasks complete. Treat the ClawHub and index pages as source material, then perform your own review before using it with sensitive repos, credentials, or external actions. Sources Awesome OpenClaw Skills: https://github.com/VoltAgent/awesome-openclaw-skills ClawHub listing: https://clawhub.ai/arminnaimi/skills/agent-team-orchestration Skill mirror: https://clawskills.sh/skills/arminnaimi-agent-team-orchestration
Free
Review open
An OpenClaw skill candidate for tracking AI-native tools, GitHub momentum, launches, funding signals, and repo traction in one briefing. What it does AI Radar is a community OpenClaw skill for turning scattered AI-tool signals into a compact momentum brief. It pairs product news with GitHub indicators such as trending status, star movement, releases, and ecosystem mentions so an agent can explain why a tool matters now instead of only listing links. Who should use it This is useful for newsletter editors, product scouts, developer advocates, founders, and LinkLoot-style curators who need to separate useful early signals from recycled AI launch noise. Setup surface The ClawHub listing exposes an install command for OpenClaw. Do not install it blindly on a production Pi. Review the SKILL.md, check the requested workflow, and run it first in a sandbox or disposable workspace with no secrets. Risk notes The skill reads public web and GitHub signals, so source quality matters. Treat third-party pages, launch posts, and repo READMEs as untrusted content. Verify claims against official project pages, releases, and independent traction signals before publishing or acting on the output. Sources Awesome OpenClaw Skills: https://github.com/VoltAgent/awesome-openclaw-skills ClawHub listing: https://clawhub.ai/lopushok9/skills/airadar Skill mirror: https://clawskills.sh/skills/lopushok9-airadar
Free
Review open
arc-trust-verifier helps review publisher, version, dependency, and attestation signals before installing a ClawHub skill. What it is arc-trust-verifier is a community OpenClaw skill for checking trust signals around ClawHub skills before you install or distribute them. Its listing says it analyzes publisher reputation, version consistency, content integrity, dependency chains, and signed attestations. Who should use it Use this as an evaluation candidate if you manage shared OpenClaw workspaces, test community skills, or need a repeatable pre-install review step for agents that can touch files, credentials, browsers, or external services. Setup surface The public listing shows install commands for OpenClaw CLI and ClawHub CLI, but this item is an editorial candidate only. Do not install it on a production OpenClaw host until you have reviewed the SKILL.md, scripts, dependency behavior, and registry metadata in a disposable environment. Risk notes The clawskills.sh page currently shows suspicious security signals from VirusTotal and OpenClaw status fields. Treat that as a reason to inspect the source carefully, not as a recommendation to run it. If you evaluate it, prefer a locked-down test workspace with no secrets and compare its claims against manual checks. Source links Awesome OpenClaw Skills lists arc-trust-verifier under Git & GitHub as a provenance and trust-score skill. clawskills.sh provides the public skill page, version notes, setup commands, and security status. ClawHub provides the registry page for the publisher and skill slug.
Free
Review open
A pre-build review skill for founders and small teams that helps challenge scope, assumptions, and implementation plans before work starts. Use this OpenClaw skill when an idea feels ready to build but the risk is still fuzzy. Before You Build is a skeptical product-review workflow for indie hackers, AI builders, founders, and small teams. Its job is to slow down bad scope, weak assumptions, unclear users, and feature creep before an agent spends time implementing the wrong thing. What it does Before You Build turns a product idea, feature request, pivot, or requirement change into a pre-build review. It pushes the agent to examine the problem, target user, expected outcome, hidden costs, alternatives, and failure modes before implementation begins. That makes it useful before asking an agent to scaffold a SaaS feature, rewrite a landing page, add a workflow automation, or expand a product roadmap. Who should use it Solo founders deciding what to build next. Product teams using agents for fast prototyping. Builders who often over-scope early versions. OpenClaw users who want a repeatable gate before code generation. Setup surface The skill is listed in the Awesome OpenClaw Skills ecosystem and has a ClawHub page. Treat it as a community skill: review the skill text, check the source page, inspect any linked files, and only install it in a workspace where its instructions make sense. Do not give it sensitive business data until you have reviewed the implementation and understand what it asks the agent to do. Risk notes Community skills are curated, not audited. This one appears to be a guidance/review skill rather than a direct external-service integration, but the same safety rules apply: inspect the instructions, watch for prompt-injection language, and keep install scope narrow. The practical value is highest when paired with a clear product brief. If the input is vague, the output may become generic. Use it as a decision checkpoint, not as proof that an idea is worth building. Source links Awesome OpenClaw Skills: https://github.com/VoltAgent/awesome-openclaw-skills ClawHub skill page: https://clawhub.ai/bin1874/before-you-build
Free
Review open
Agent Builder is a community OpenClaw skill candidate for designing agent workspaces, guardrails, memory posture, and acceptance tests before deployment. What it does Agent Builder is an OpenClaw community skill candidate for creating or refining an agent workspace. The useful part is the checklist: it asks for the agent mission, channels, autonomy level, hard prohibitions, memory posture, tone, and tool behavior before generating files such as IDENTITY.md, SOUL.md, AGENTS.md, USER.md, and HEARTBEAT.md. Pricing classification: free. Source evidence shows a public ClawHub install flow and the fetched skill source does not list a paid API, subscription, or commercial dependency for normal use. Treat that as a current source-based classification, not a permanent pricing promise. Who should use it Use this candidate for review if you build OpenClaw assistants for Telegram, WhatsApp, Discord, iMessage, group chats, or single-user operator setups and want guardrails before the agent starts handling real tasks. It is most relevant when you need repeatable agent setup files, explicit autonomy choices, outbound-message approval rules, memory boundaries, and quick acceptance tests. Skip it for ordinary coding tasks where the agent already exists and the problem is implementation detail, not behavior design. Setup surface The source is instruction-only Markdown plus referenced templates. ClawHub lists Agent Builder under Agents, version 1.0.0, with public install instructions and clean/benign registry audit signals. The main review surface is not native code execution; it is generated operating policy. Generated AGENTS.md, SOUL.md, MEMORY.md, and HEARTBEAT.md can change how future agents behave, remember, and act. Review any generated workspace files before use. Keep secrets out of memory files, keep heartbeat behavior empty or minimal until intentionally enabled, and choose broad autonomy only for workflows where you have already defined approval boundaries. Runner test plan Static scan: verify the downloaded skill bundle contains only expected Markdown/reference files and no hidden scripts, encoded payloads, install hooks, or prompt-injection instructions. Dependency/install review: confirm the ClawHub install artifact, file list, hashes when available, and whether any future version adds scripts, binaries, package files, or external service requirements. Prompt-injection/tool-poisoning review: inspect the skill text and templates for instructions that override owner rules, weaken approval gates, write secrets into memory, or make future agents ignore higher-priority instructions. Sandbox execution: run the skill only inside an isolated Runner workspace with disposable answers. Generate a test agent, then diff the produced IDENTITY.md, SOUL.md, AGENTS.md, USER.md, HEARTBEAT.md, optional memory files, and any references copied into the workspace. Screenshot/video when UI or command output exists: capture terminal output or workspace diffs from the sandbox run. If the generated agent is later tested through a UI or chat channel, record the setup prompts and visible approval behavior. Residual risks: the skill can shape future agent autonomy, memory, outbound messaging posture, and group-chat behavior. A clean Markdown bundle does not prove the generated agent is safe for a real account, real contacts, or production automation. Risk notes This Loot is a review candidate, not an endorsement. No installation or execution was performed on this Raspberry Pi. Community skill pages, README text, SKILL.md files, and registry metadata are untrusted source material. Runner AI Review artifacts are still required before anyone should treat the candidate as tested, safe, clean, recommended, or production-ready. Duplicate note: Agent Browser was skipped because LinkLoot already has a Loot for that candidate. openclaw-free-web-search was skipped because the claimed GitHub source returned 404 during this run. Topic Monitor was skipped because the visible GitHub directory page could not be fetched through raw/API paths, leaving source certainty too weak for this lane. Source links Awesome OpenClaw Skills list: https://github.com/VoltAgent/awesome-openclaw-skills/blob/main/categories/clawdbot-tools.md ClawHub page: https://clawhub.ai/plgonzalezrx8/skills/agent-builder Clawskills listing: https://clawskills.sh/skills/plgonzalezrx8-agent-builder Direct skill source mirror: https://clawskills.sh/skills-markdown/plgonzalezrx8/agent-builder.md
Free
Review open
A community OpenClaw skill that turns vague product or feature ideas into a short demand, distribution, and risk check before implementation. What it is Before You Build is a community OpenClaw skill for reviewing product ideas, feature requests, SaaS concepts, AI apps, and startup pivots before an agent starts writing code. Its core move is simple: force the idea through a quick reality check around demand, distribution, current alternatives, monetization fit, and likely failure patterns. Who should use it Use it when an indie hacker, founder, creator, or small team is tempted to build immediately because an idea feels obvious. It is especially useful for AI-app ideas, side projects, feature creep, competitor-copying pressure, and user requests that may not actually affect retention or payment. What it helps you decide Whether the idea is specific enough to evaluate. Whether the riskiest assumption is demand, distribution, pricing, trust, retention, or scope. Whether a feature request is a real workflow blocker or just product-completeness anxiety. Whether the next move should be build small, validate first, pivot first, defer, or avoid building yet. Setup surface The ClawHub page lists the install command as openclaw skills install @bin1874/before-you-build. Treat that as a setup lead, not an endorsement. Review the visible SKILL.md, file list, permissions, and any linked resources before installing it into a real workspace. Risk notes This is an editorial candidate, not a tested recommendation. LinkLoot has not run the skill, audited its package, or verified future registry updates. Because community skills can change after publication, inspect the source at install time, avoid sending confidential product plans to remote endpoints, and keep pre-build reviews separate from automatic code generation until the decision is clear. Source links Awesome OpenClaw Skills Before You Build on ClawHub
Free
Review open
A free OpenClaw community skill candidate for local speech-to-text, subtitles, diarization, transcript search, podcast or URL input, and batch transcription workflows. What it does Faster Whisper is an OpenClaw community skill for local audio and video transcription. The ClawHub page and GitHub repository describe faster-whisper based speech-to-text, SRT/VTT/TTML/CSV subtitle output, speaker diarization, URL and YouTube input, podcast feed processing, batch mode, transcript search, chapter detection, translation to English, noisy-audio preprocessing, and per-file language handling. The useful LinkLoot angle is simple: an OpenClaw agent can turn recordings, interviews, lectures, podcasts, or video files into structured text without starting from a hosted transcription API. That can matter for cost, privacy, offline work after model download, and repeatable media pipelines. Who should use it Use this as a candidate if your OpenClaw workflow regularly handles meetings, creator clips, interviews, lectures, voice notes, podcasts, subtitles, or archive search. It fits local-first operators who want an agent to manage transcription steps and output formats instead of manually running a separate tool each time. It is less useful if your machine cannot handle local models, if you need enterprise transcription guarantees, or if your workflow already depends on a reviewed hosted provider with retention, compliance, and speaker-labeling controls. Setup surface ClawHub lists the package as @theplasmak/faster-whisper with the install command openclaw skills install @theplasmak/faster-whisper. The underlying GitHub repository is reachable and shows Python, shell, PowerShell, and batch surfaces, plus standalone setup scripts and transcription scripts. The GitHub page lists an MIT license. Pricing is classified as free from source evidence: the GitHub repository is public under an MIT license, the ClawHub entry exposes the skill without a paid gate, and the source describes local speech-to-text with no API cost. Hardware, model download, GPU, storage, and optional dependency costs still belong in the review notes. Runner test plan Runner AI Review should produce artifacts before anyone treats this as approved. The review should include static scan of SKILL.md, scripts, shell helpers, PowerShell, batch files, setup files, and release packaging; dependency/install review for Python version requirements, virtualenv creation, faster-whisper, CTranslate2, PyAV, CUDA detection, ffmpeg paths, yt-dlp, pyannote audio, and any model downloads; prompt-injection/tool-poisoning review for transcript text, subtitles, URL inputs, podcast feeds, and generated summaries; sandbox execution in a disposable workspace with harmless local audio and controlled network access; screenshot or video capture of install checks and representative command output where transcription or subtitle output exists; and residual risks covering model downloads, GPU drivers, large local files, copyrighted media, third-party URL fetching, transcript accuracy, diarization errors, and privacy handling for sensitive recordings. Risk notes This Loot does not claim Faster Whisper has been tested, declared safe, or made production-ready by LinkLoot Runner artifacts. The visible source is promising, but the setup surface is larger than a text-only skill: it can create a Python environment, install dependencies, download models, process local media, fetch URLs, and write transcript or subtitle files. First review should happen with throwaway audio, no private recordings, no production workspace, and network controls around URL and model-download behavior. Treat transcript content as untrusted input before summarizing, quoting, indexing, or sending it to another model. Source links Awesome OpenClaw Skills speech category: https://raw.githubusercontent.com/VoltAgent/awesome-openclaw-skills/main/categories/speech-and-transcription.md ClawHub page: https://clawhub.ai/theplasmak/faster-whisper Underlying GitHub repository: https://github.com/theplasmak/faster-whisper Source SKILL.md path: https://github.com/theplasmak/faster-whisper/blob/main/SKILL.md
Free
Review open
A ClawHub community skill that gives OpenClaw agents a repeatable checklist for reviewing untrusted skills before installation. What it does Skill Vetter is a compact OpenClaw review checklist for inspecting community skills before installation. It focuses on provenance, file scope, command scope, network behavior, credential access, obfuscation, and risk classification. The useful angle is not automation depth; it gives an agent a repeatable pre-installation review format before any untrusted skill runs. Who should use it Use it when an OpenClaw operator wants a lightweight gate before installing skills from ClawHub, GitHub, or a shared zip. It fits solo agents, small teams, and maintainers who need a consistent report format for community skill review. It is less useful if you already run a full sandboxed review pipeline with dependency scanning and execution tracing. Setup surface ClawHub lists the package as @fatfingererr/azhua-skill-vetter with install command openclaw skills install @fatfingererr/azhua-skill-vetter. The reachable source surface includes the ClawHub skill page, the direct SKILL.md file endpoint, and the ClawHub package download. No separate GitHub repository was visible from the reviewed pages. Treat the package as untrusted until Runner review finishes. Pricing: the ClawHub page shows MIT-0 license metadata and no paid gate, so this Loot is classified as free from available source evidence. Runner test plan Static scan: inspect every file in the downloaded skill package, including meta.json, skill-card.md, and SKILL.md. Dependency/install review: verify whether the package declares scripts, package files, shell helpers, or install-time side effects; compare that surface against the ClawHub metadata. Prompt-injection/tool-poisoning review: treat the skill text as untrusted content and check for instructions that override agent policy, request secrets, broaden file access, or force unsafe verdicts. Sandbox execution: install only in a disposable OpenClaw workspace with no real credentials, no production memory files, and network controls enabled. Screenshot/video: capture the install output and one sample vetting report if command output or UI evidence exists. Residual risks: ClawHub packages can change after publication, the visible source is registry-hosted rather than a GitHub repo with independent commit history, and the skill's own checklist language should not replace human approval for high-risk installs. Risk notes The candidate is security-themed, but that does not make it reviewed or safe. It includes suggested curl commands for GitHub-hosted skills; those should be treated as examples for a sandboxed reviewer, not commands to run blindly. The strongest limitation is source transparency: a direct SKILL.md path is reachable, but no underlying GitHub repository was visible during this pass. Source links Awesome OpenClaw Skills list: https://github.com/VoltAgent/awesome-openclaw-skills/blob/main/README.md?plain=1L240 ClawHub page: https://clawhub.ai/fatfingererr/azhua-skill-vetter Independent index page: https://clawskills.sh/skills/fatfingererr-azhua-skill-vetter Reachable SKILL.md source: https://clawhub.ai/api/v1/skills/azhua-skill-vetter/file?path=SKILL.md Reachable package download: https://wry-manatee-359.convex.site/api/v1/download?slug=azhua-skill-vetter
Free
Review open
A code-backed OpenClaw skill for live search, page extraction, crawl/map flows, and evidence packs with a no-key baseline plus optional provider upgrades. What it does Web Search Pro is a Node-based OpenClaw skill for agents that need more than a single search result page. It exposes live web search, news search, docs lookup, URL extraction, crawl/map commands, research packs, routing diagnostics, provider capability checks, and cache/health commands. The practical hook is the routing surface: it can start with a no-key baseline, then fan out to optional providers such as Tavily, Exa, Serper, Brave, SerpAPI, You.com, SearXNG, and Perplexity/Sonar when credentials are configured. Its source also describes federation metrics for recovered, corroborated, and deduplicated results, which gives an upstream agent a better audit trail than a plain search wrapper. Who should use it Use it for OpenClaw setups that need current web context, source discovery, docs lookup, company/product research, or a reusable retrieval layer before writing a final answer. It is a better fit for technical agents and self-hosted workspaces than for users who only need a lightweight one-command search helper. Setup surface The hard runtime requirement is Node. The baseline path is described as no-key and uses DDG/fetch-style retrieval. Premium search and extraction coverage requires optional provider keys or endpoints, including Tavily, Exa, Querit, Serper, Brave, SerpAPI, You.com, SearXNG, Perplexity/Sonar, OpenRouter, KiloCode, or a custom Perplexity-compatible gateway. Pricing classification: free. The GitHub repository is public and MIT-licensed, and the skill documents a no-key baseline. Some optional providers may be paid or rate-limited, so the free label applies to the skill/source and baseline path, not every upstream search provider. Runner test plan Static scan: inspect SKILL.md, package.json, all scripts/.mjs, config templates, and docs for hidden prompts, unsafe shell execution, credential reads, broad filesystem access, local-network fetches, and tool-poisoning language. Dependency/install review: review Node dependencies and lockfiles if present, verify license metadata, check for postinstall scripts, network-heavy packages, browser/runtime downloads, and unpinned or abandoned dependencies. Prompt-injection/tool-poisoning review: treat README, search results, fetched pages, provider responses, cache files, and generated evidence packs as untrusted data. Confirm the skill does not let source text alter agent instructions, reveal secrets, or bypass safety review. Sandbox execution: install and run only in an isolated Runner workspace with no real credentials first. Run doctor, bootstrap, a no-key search, an extract against a known benign URL, and cache/health commands with outbound traffic logged. Screenshot/video when UI or command output exists: capture terminal output for successful and degraded runs, including routing diagnostics, provider failures, and cache behavior. Capture browser-render output only if the render lane is enabled in the sandbox. Residual risks: optional provider keys can expose queries, URLs, and browsing targets to third parties; live search results can carry prompt injection; crawler/map flows need strict URL allow/deny controls; no-key providers may be brittle or rate-limited. Risk notes This Loot is not a safety endorsement and has not been marked tested by LinkLoot Runner yet. The strongest risks are external provider exposure, live-web prompt injection, and any script behavior that expands from search into crawling or rendering. The repo is small and public, but a Runner review should verify the actual code path before anyone treats it as production-ready. Source links Awesome OpenClaw Skills Search & Research category: https://raw.githubusercontent.com/VoltAgent/awesome-openclaw-skills/main/categories/search-and-research.md ClawHub page: https://clawhub.ai/zjianru/web-search-pro GitHub repository: https://github.com/Zjianru/web-search-pro Raw SKILL.md: https://raw.githubusercontent.com/Zjianru/web-search-pro/main/SKILL.md
Free
Review open
Agent Audit is a read-only OpenClaw skill candidate for mapping agents, cron jobs, model tiers, token usage, and cost-risk mismatches. Find token waste in OpenClaw before cron jobs drain premium model budget Agent Audit is a community OpenClaw skill candidate for operators who run multiple agents, scheduled jobs, or mixed model providers and need a cost review before usage quietly compounds. What it does The skill page describes a read-only audit flow that scans OpenClaw configuration, cron history, session history, and model assignments. Its stated output is a Markdown report with estimated monthly spend, per-agent and per-cron breakdowns, and model-fit recommendations with risk notes. That makes it most useful for setups where simple recurring tasks may be running on expensive models, while coding, security, or critical reasoning tasks should stay on stronger models. Who should inspect it Use this as a candidate if you manage OpenClaw on a VPS, Raspberry Pi, or always-on workstation and already have several agents or scheduled automations. It is less useful for a single-agent install with little run history. Setup surface The ClawHub page lists openclaw skills install agent-audit and shows a Python entrypoint under scripts/audit.py. Review the SKILL.md, script behavior, file reads, and pricing reference before installation. Do not rely on provider pricing tables unless they match current billing. Risk notes LinkLoot has not run this skill. Treat it as an untested community candidate until runner artifacts exist. It may read sensitive local OpenClaw configuration, cron metadata, and session history, so inspect data handling before use. Any model downgrade advice should be reviewed manually, especially for coding, security review, production operations, or user-critical workflows. Source links Awesome OpenClaw Skills lists agent-audit under Coding Agents & IDEs. Clawskills mirrors the public listing and summarizes the workflow. ClawHub hosts the registry page, install surface, SKILL.md content, version, license, and security status fields.
Free
Review open
An OpenClaw skill candidate that bundles TODO/FIXME loop scans, parallel-vs-serial planning, file-size review, and subworkflow handoff into one local workflow surface. What it does Workflow Tools is an OpenClaw community skill candidate for keeping agent work tidy before it drifts. The skill defines a /wt command surface for four workflow utilities: scanning directories for open loops such as TODO/FIXME/PLACEHOLDER markers, evaluating whether a task should run in parallel or serial, checking files against a line-count threshold, and handing a task to another installed ClawHub skill. Pricing classification: free. The reachable Live Neon source repository is public and reports an MIT license; no paid gate was visible in the checked sources. Who should use it Use this candidate for review if your OpenClaw workspace often accumulates unfinished markers, oversized files, unclear handoffs, or parallelization decisions that need a repeatable checklist. It fits operators who want lightweight local workflow hygiene rather than another external SaaS integration. Setup surface The skill declares config files under .openclaw/workflow-tools.yaml and .claude/workflow-tools.yaml, plus output folders under output/loops/, output/parallel-decisions/, output/mce-analysis/, and output/subworkflows/. Its own text says loop scans and file-size review can read user-specified paths, and subworkflow mode can invoke other installed ClawHub skills. No installation or execution was performed on this Raspberry Pi. Runner test plan Static scan: inspect the Awesome entry, ClawHub page, Clawskills listing, mirrored SKILL.md, Live Neon source tree, raw SKILL.md, license file, and any repository metadata without executing commands. Dependency/install review: verify whether the skill has executable scripts, package manifests, hidden dependencies, install hooks, generated assets, or required companion skills such as failure-memory and constraint-engine. Prompt-injection/tool-poisoning review: check the SKILL.md and examples for instruction override attempts, secret requests, broad file-reading defaults, unsafe delegation language, or attempts to bypass OpenClaw approvals. Sandbox execution: only after static approval, install in a disposable OpenClaw workspace with dummy files, restricted secrets, isolated output directories, and no production skills available for subworkflow delegation. Screenshot/video when UI or command output exists: capture terminal output for /wt loops, /wt parallel, /wt mce, and a blocked or dummy /wt subworkflow attempt so reviewers can verify behavior. Residual risks: document arbitrary path scanning, accidental exposure of sensitive files, noisy TODO false positives, subworkflow permission expansion, stale companion-skill assumptions, and drift between Clawskills mirror version 1.4.0 and Live Neon source version 1.5.0. Risk notes This Loot is a review candidate, not a safety endorsement. Community skill text is untrusted input. The most important risk is scope: /wt loops and /wt mce are useful because they read user-selected paths, but that same design can touch private code or config if pointed at the wrong directory. Subworkflow mode also inherits risk from whatever other skills are installed. Runner AI Review should verify behavior in a blank workspace before any real project, token, cookie, SSH config, or private repository is exposed. Source links Awesome OpenClaw Skills category entry: https://raw.githubusercontent.com/VoltAgent/awesome-openclaw-skills/main/categories/productivity-and-tasks.md ClawHub page: https://clawhub.ai/leegitw/workflow-tools Clawskills listing: https://clawskills.sh/skills/leegitw-workflow-tools Clawskills SKILL.md mirror: https://clawskills.sh/skills-markdown/leegitw/workflow-tools.md Underlying Live Neon source tree: https://github.com/live-neon/skills/tree/main/agentic/workflow-tools Raw SKILL.md source: https://raw.githubusercontent.com/live-neon/skills/main/agentic/workflow-tools/SKILL.md License evidence: https://raw.githubusercontent.com/live-neon/skills/main/LICENSE
Free
Review open
An OpenClaw Runner-review candidate for separating agent proposals from approved execution, with replay protection, receipts, and offline signature checks. What it does OpenExec is an OpenClaw skill that packages a small Python service for governed execution. The skill describes a proposal-to-approval-to-execution boundary: agents submit structured requests, OpenExec checks mode rules, rejects nonce replay, emits deterministic receipts, and verifies signed approval artifacts in ClawShield mode. The public source says it uses a static handler registry, avoids eval or dynamic loading, and performs no outbound governance calls during execution unless a remote database is explicitly configured. Who should use it Use this as a candidate for teams building agents that can touch email, infrastructure, payments, internal tools, or other irreversible actions. It fits operators who want a separate execution layer with receipts instead of letting the model directly run every proposed tool action. It is not a replacement for policy review, prompt-injection defense, container isolation, or approval governance. Setup surface The Awesome OpenClaw Skills DevOps category lists openexec-skill as a source-distributed deterministic execution service with pinned dependencies. ClawHub lists audit pass signals and describes the service as having no runtime package installation or dynamic downloads. The source tree exposes SKILL.md, SECURITY.md, README.md, main.py, requirements, tests, scripts, and configuration folders. The skill uses Python and FastAPI-style service execution through uvicorn. Pricing evidence: SKILL.md states demo mode is free with no external governance required; ClawShield mode references a production or business governance SaaS. Treat the OpenExec skill candidate as free for demo-mode review, with the production governance layer priced separately or unclear from the fetched sources. Runner test plan Static scan: inspect SKILL.md, README.md, SECURITY.md, main.py, requirements, tests, scripts, config, and handler registry files. Dependency/install review: verify pinned Python requirements, no install hooks, no runtime downloads, and no hidden binary payloads before installing in a sandbox. Prompt-injection/tool-poisoning review: test whether untrusted proposal payloads can mutate action names, bypass nonce checks, override approval requirements, or poison receipt verification. Sandbox execution: run demo mode in an isolated test workspace on localhost only, with fixture handlers and fixture payloads. Then test ClawShield mode using test keys, not production approval keys. Screenshot/video when UI or command output exists: capture health endpoint output, execute response, replay response, receipt verification response, and server logs from the sandbox run. No browser UI is expected. Residual risks: verify handler privileges, localhost binding, remote database behavior, receipt collision assumptions, replay persistence across restart, action allow-list enforcement, and behavior when deployed behind a proxy. Risk notes This is not a tested recommendation yet. OpenExec is an execution boundary, not an OS sandbox. Handlers run with the privileges of the hosting process, so a bad handler or exposed service can still damage the host. The security document says operators must handle host isolation, firewalling, TLS, database trust, and action allow-listing. The fetched GitHub HTML confirms main.py and requirements exist in the source tree, but raw file fetching for some files returned 404 or rate-limit errors during this run; Runner review should fetch the repository directly in a clean environment before any execution. Source links Awesome OpenClaw Skills DevOps category: https://github.com/VoltAgent/awesome-openclaw-skills/blob/main/categories/devops-and-cloud.md Clawskills listing: https://clawskills.sh/skills/trendinghot-openexec-skill ClawHub page: https://clawhub.ai/trendinghot/openexec-skill Source tree: https://github.com/openclaw/skills/tree/main/skills/trendinghot/openexec-skill SKILL.md source page: https://github.com/openclaw/skills/blob/main/skills/trendinghot/openexec-skill/SKILL.md SECURITY.md source page: https://github.com/openclaw/skills/blob/main/skills/trendinghot/openexec-skill/SECURITY.md
Free
Review open
Blog
Related reads
No blog posts for #agent yet
There is no published article with this tag right now. Browse the blog for adjacent themes or follow the tag for future updates.