{"skill":{"slug":"agent-runtime-security","displayName":"Agent Runtime Security","summary":"Complete OpenClaw Agent Security Hardening - Protects against data leaks (storage security) and prompt injection (runtime security). Use for initial setup, s...","tags":{"agent-protection":"1.0.0","command-safety":"1.0.0","latest":"1.0.0","prompt-injection":"1.0.0","runtime-security":"1.0.0","three-question-test":"1.0.0"},"stats":{"comments":0,"downloads":258,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1773737317171,"updatedAt":1777358210493},"latestVersion":{"version":"1.0.0","createdAt":1773737317171,"changelog":"Initial release. Runtime security framework for OpenClaw agents based on real-world prompt injection attack (March 8, 2026).\nFeatures:\n- Dynamic Security: Content vs Intent detection, Three-Question Test\n- Static Security: File permissions, .env isolation, Git protection\n- Real attack case analysis and prevention patterns\n- Automated monitoring scripts (security-check.sh)\n- Testing suite and examples for agent developers\nUse Cases:\n- Prevent agents from executing commands found in error logs/docs\n- Protect against prompt injection attacks\n- Safe execution patterns for dangerous commands\nComplements kylejfrost/openclaw-security-hardening (skill file scanning).\nThis skill protects agents during runtime execution.","license":"MIT-0"},"metadata":null,"owner":{"handle":"qingquanagi","userId":"s17dvqcnfw6y9naq068ze22hzh83yvkb","displayName":"qingquanagi","image":"https://avatars.githubusercontent.com/u/13479952?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.prompt_injection_instructions"],"summary":"Detected: suspicious.prompt_injection_instructions","engineVersion":"v2.4.2","updatedAt":1777358210493}}