{"id":"50a59053-d102-4b9f-a5d2-c5d552162c9b","slug":"npm-ai-sentinel","name":"ai-sentinel","description":"OpenClaw plugin for prompt injection detection. Drop-in security scanning that hooks into message, tool call, and tool result lifecycle events using heuristic pattern matching. For the full SDK with ML classification, custom rules, and audit logging, see","canonicalUrl":"https://www.xpersona.co/skill/npm-ai-sentinel","sourceUrl":"https://github.com/zetro-ai/ai-sentinel","homepage":"https://zetro.ai","source":"GITHUB_OPENCLEW","vendor":{"slug":"zetro","label":"Zetro","url":"https://zetro.ai"},"protocols":["MCP","OPENCLEW"],"capabilities":["openclaw","openclaw-plugin","ai-security","prompt-injection","jailbreak-detection","llm-security","ai-sentinel","threat-detection","agent-security"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"0.2.1","freshnessAt":"2026-04-15T00:59:39.223Z","freshnessLabel":"Apr 15, 2026","securityReviewed":true,"openapiReady":true,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP, OpenClaw"},{"label":"Freshness","value":"Apr 15, 2026"},{"label":"Vendor","value":"Zetro"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"0.2.1"}],"factsPreview":[{"factKey":"vendor","label":"Vendor","value":"Zetro","category":"vendor","href":"https://zetro.ai","sourceUrl":"https://zetro.ai","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T00:59:39.224Z","isPublic":true,"metadata":{}},{"factKey":"protocols","label":"Protocol compatibility","value":"MCP, OpenClaw","category":"compatibility","href":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/contract","sourceType":"contract","confidence":"high","observedAt":"2026-02-24T20:00:39.023Z","isPublic":true,"metadata":{}},{"factKey":"auth_modes","label":"Auth modes","value":"mcp","category":"compatibility","href":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/contract","sourceType":"contract","confidence":"high","observedAt":"2026-02-24T20:00:39.023Z","isPublic":true,"metadata":{}},{"factKey":"schema_refs","label":"Machine-readable schemas","value":"OpenAPI or schema references published","category":"artifact","href":"https://github.com/zetro-ai/ai-sentinel#input","sourceUrl":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/contract","sourceType":"contract","confidence":"high","observedAt":"2026-02-24T20:00:39.023Z","isPublic":true,"metadata":{}},{"factKey":"handshake_status","label":"Handshake status","value":"UNKNOWN","category":"security","href":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/npm-ai-sentinel/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true,"metadata":{}}],"highlights":["Schema refs published","Trust evidence available"],"agentCard":{"name":"ai-sentinel","description":"OpenClaw plugin for prompt injection detection. Drop-in security scanning that hooks into message, tool call, and tool result lifecycle events using heuristic pattern matching. For the full SDK with ML classification, custom rules, and audit logging, see","source":"GITHUB_OPENCLEW","sourceId":"npm:ai-sentinel","homepage":"https://zetro.ai","repository":"https://github.com/zetro-ai/ai-sentinel","documentation":"https://www.xpersona.co/skill/npm-ai-sentinel/agent/npm-ai-sentinel","protocols":["MCP","OPENCLEW"],"capabilities":["openclaw","openclaw-plugin","ai-security","prompt-injection","jailbreak-detection","llm-security","ai-sentinel","threat-detection","agent-security"],"languages":["typescript"],"install":{"command":"git clone https://github.com/zetro-ai/ai-sentinel.git","ecosystem":"git"}}}