{"data":{"slug":"gk0wk-clawguard","name":"ClawGuard","tagline":"Security tool for OpenClaw, covering dangerous action approval, scanning skills, blocking secret leaks.","github_url":"https://github.com/Gk0Wk/ClawGuard","owner":"Gk0Wk","repo":"ClawGuard","owner_avatar_url":"https://avatars.githubusercontent.com/u/16955102?v=4","primary_language":"TypeScript","stars":87,"forks":2,"topics":["agent-security","ai-security","audit-logs","cybersecurity","data-loss-prevention","guardrails","human-in-the-loop","llm-security","open-source","openclaw","policy-engine","prompt-injection","runtime-security","secret-scanning","supply-chain-security"],"archived":false,"github_pushed_at":"2026-03-20T08:07:15+00:00","maintenance_label":"Slowing","stars_delta_30d":-12,"url":"https://www.graphcanon.com/tools/gk0wk-clawguard","markdown_url":"https://www.graphcanon.com/tools/gk0wk-clawguard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/gk0wk-clawguard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=gk0wk-clawguard","description":"The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in control, for safety.","homepage_url":"https://clawguard.top","license":null,"open_issues":5,"watchers":1,"ai_summary":"ClawGuard is an AI security agent designed to enhance safety within the OpenClaw environment by approving risky actions, scanning skills and secrets for security issues, and maintaining human oversight in critical processes. It operates as a plugin for OpenClaw, emphasizing runtime and data loss prevention, prompt injection defense, and audit logging.","readme_excerpt":"## Install demo\n\nThe install-demo entry lives here:\n\n- [`plugins/openclaw-clawguard/README.md`](./plugins/openclaw-clawguard/README.md)\n\nRecommended install method from the repo root:\n\n```powershell\nopenclaw plugins install .\\plugins\\openclaw-clawguard\n```\n\nOptional local tarball demo only:\n\n```powershell\npnpm --dir plugins\\openclaw-clawguard pack\nopenclaw plugins install .\\plugins\\openclaw-clawguard\\<generated-tarball>.tgz\n```\n\nImportant posture:\n\n- this is an **install demo only**,\n- it is **not published to a registry**,\n- `@clawguard/clawguard` is currently **metadata only and still unpublished**,\n- and this README does **not** imply npm publish, GA, or a formal release.\n\nAfter install, restart OpenClaw, then use the plugin README operator runbook for the smoke path, 1-minute demo order, and 3-minute demo order. The current smoke path is:\n\n- run `openclaw dashboard --no-open`\n- replace the official tokenized dashboard URL path with `/clawguard`\n- if bare `/clawguard` has no current-tab token yet, the public shell now shows a connect page aligned with OpenClaw Control UI bootstrap instead of failing closed\n- then move through:\n  - `/clawguard`\n  - `/clawguard/checkup`\n  - `/clawguard/approvals`\n  - `/clawguard/audit`\n  - `/clawguard/settings`","github_created_at":"2026-03-11T11:53:25+00:00","created_at":"2026-07-15T10:43:32.139322+00:00","updated_at":"2026-09-20T04:26:07.156191+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent-security","name":"agent-security"},{"slug":"ai-security","name":"ai-security"},{"slug":"audit-logs","name":"audit-logs"},{"slug":"cybersecurity","name":"cybersecurity"},{"slug":"data-loss-prevention","name":"data-loss-prevention"},{"slug":"guardrails","name":"guardrails"},{"slug":"human-in-the-loop","name":"human-in-the-loop"},{"slug":"llm-security","name":"llm-security"}],"trust":{"provenance":{"is_fork":false,"github_id":1178814821,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-12T06:00:36.699Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":175,"last_release_at":"2026-03-13T09:31:20Z","stars_delta_30d":-12,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":10,"high_count":0,"last_scan_at":"2026-07-15T10:43:33.437Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-12T06:00:37.139Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-12T06:00:37.139Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-12T06:00:37.139Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Installation of ClawGuard requires the use of PowerShell commands or pnpm for package management. This is specific to its context within OpenClaw."],"requires_docker":false},"constraints":{"runtime":"unknown","requires_docker":false},"when_to_use":["If you are using the OpenClaw environment and require specific security measures tailored to this ecosystem.","When you need a tool that integrates seamlessly with runtime and data loss prevention techniques in an AI application context."],"when_not_to_use":["Do not use ClawGuard if your project is not within the OpenClaw framework, as its features are designed for integration with it.","Avoid using this tool if you require a plugin that has been formally released or certified; ClawGuard is still in development and uses metadata-only packages, without formal releases."],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:32:09.742Z"},"constraint_facets":{"runtime":"unknown","requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Installation of ClawGuard requires the use of PowerShell commands or pnpm for package management. This is specific to its context within OpenClaw."},{"label":"Adopt for","value":"ClawGuard is an AI security agent for OpenClaw that focuses on enhancing safety through the approval of risky actions, scanning skills and secrets for security issues, maintaining audit logs for critical processes."},{"label":"License detail","value":"(Not disclosed)"},{"label":"Runtime","value":"unknown"}]}}