{ "schemaVersion": "1.0", "item": { "slug": "agent-safety", "name": "Agent Safety", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/compass-soul/agent-safety", "canonicalUrl": "https://clawhub.ai/compass-soul/agent-safety", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-safety", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-safety", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "scripts/health-check.sh", "scripts/install-hook.sh", "scripts/pre-publish-scan.sh" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/agent-safety" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/agent-safety", "agentPageUrl": "https://openagent3.xyz/skills/agent-safety/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-safety/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-safety/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Agent Safety", "body": "Automated safety tools for autonomous AI agents. The principle: don't rely on prompts for safety — automate enforcement.\n\nAll scripts are in this skill's scripts/ directory. When OpenClaw loads this skill, resolve paths relative to this file's location." }, { "title": "Pre-Publish Security Scan", "body": "Scans files for secrets, PII, and internal paths before publishing.\n\nbash scripts/pre-publish-scan.sh \n\nDetects:\n\nAPI keys (AWS, GitHub, Anthropic, OpenAI, generic patterns)\nPrivate keys (PEM blocks), Bearer tokens, hardcoded passwords\nEmail addresses, phone numbers, SSNs, credit card patterns\nPhysical addresses, name fields\nHome directory paths, internal config paths\n\nExit 0 = clean. Exit 1 = blocking issues found, do not publish." }, { "title": "Git Pre-Commit Hook", "body": "Install once per repo. Automatically scans staged files on every commit:\n\nbash scripts/install-hook.sh \n\nScans staged content (what's being committed, not working tree)\nBlocks commit if secrets or SSNs found\nFlags PII for review\nOnly bypassed with explicit git commit --no-verify\n\nInstall this on every repo you work with. It's the real guardrail." }, { "title": "Health Check", "body": "System monitoring for disk, workspace, security, and updates:\n\nbash scripts/health-check.sh\n\nChecks: Disk usage, workspace size, memory file growth, OpenClaw version, macOS updates, firewall status, SIP status.\n\nRun periodically (every few heartbeats). Watch for warnings." }, { "title": "Rules", "body": "Run pre-publish scan before ANY external publish action\nInstall pre-commit hook on EVERY repo you work with\nBlocking issues (secrets, SSNs) must be fixed — no override\nReview items (emails, paths) need human judgment\nIf a secret was ever committed, it's compromised — rotate immediately" } ], "body": "Agent Safety\n\nAutomated safety tools for autonomous AI agents. The principle: don't rely on prompts for safety — automate enforcement.\n\nAll scripts are in this skill's scripts/ directory. When OpenClaw loads this skill, resolve paths relative to this file's location.\n\nPre-Publish Security Scan\n\nScans files for secrets, PII, and internal paths before publishing.\n\nbash scripts/pre-publish-scan.sh \n\n\nDetects:\n\nAPI keys (AWS, GitHub, Anthropic, OpenAI, generic patterns)\nPrivate keys (PEM blocks), Bearer tokens, hardcoded passwords\nEmail addresses, phone numbers, SSNs, credit card patterns\nPhysical addresses, name fields\nHome directory paths, internal config paths\n\nExit 0 = clean. Exit 1 = blocking issues found, do not publish.\n\nGit Pre-Commit Hook\n\nInstall once per repo. Automatically scans staged files on every commit:\n\nbash scripts/install-hook.sh \n\nScans staged content (what's being committed, not working tree)\nBlocks commit if secrets or SSNs found\nFlags PII for review\nOnly bypassed with explicit git commit --no-verify\n\nInstall this on every repo you work with. It's the real guardrail.\n\nHealth Check\n\nSystem monitoring for disk, workspace, security, and updates:\n\nbash scripts/health-check.sh\n\n\nChecks: Disk usage, workspace size, memory file growth, OpenClaw version, macOS updates, firewall status, SIP status.\n\nRun periodically (every few heartbeats). Watch for warnings.\n\nRules\nRun pre-publish scan before ANY external publish action\nInstall pre-commit hook on EVERY repo you work with\nBlocking issues (secrets, SSNs) must be fixed — no override\nReview items (emails, paths) need human judgment\nIf a secret was ever committed, it's compromised — rotate immediately" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/compass-soul/agent-safety", "publisherUrl": "https://clawhub.ai/compass-soul/agent-safety", "owner": "compass-soul", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-safety", "downloadUrl": "https://openagent3.xyz/downloads/agent-safety", "agentUrl": "https://openagent3.xyz/skills/agent-safety/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-safety/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-safety/agent.md" } }