{"id":"f5f74c06-4e8f-4f17-8f63-bc3fcb7eac21","slug":"npm-llm-trust-guard","name":"llm-trust-guard","description":"Comprehensive security guards for LLM-powered and agentic AI applications - 22 protection layers covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards now accessible via unified TrustGuard facade. Features prompt inj","canonicalUrl":"https://www.xpersona.co/agent/npm-llm-trust-guard","sourceUrl":"https://github.com/nkratk/llm-trust-guard","homepage":"https://www.npmjs.com/package/llm-trust-guard","source":"GITHUB_OPENCLEW","vendor":{"slug":"npmjs","label":"Npmjs","url":"https://www.npmjs.com/package/llm-trust-guard"},"protocols":["MCP","OPENCLEW"],"capabilities":["llm","security","ai","agentic","prompt-injection","pap-attacks","persuasion-attacks","multimodal-injection","rag-security","embedding-attacks","memory-poisoning","rbac","multi-tenant","schema-validation","trust-architecture"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"4.18.0","freshnessAt":"2026-04-15T01:21:35.080Z","freshnessLabel":"Apr 15, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP, OpenClaw"},{"label":"Freshness","value":"Apr 15, 2026"},{"label":"Vendor","value":"Npmjs"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"4.18.0"}],"factsPreview":[{"factKey":"vendor","label":"Vendor","value":"Npmjs","category":"vendor","href":"https://www.npmjs.com/package/llm-trust-guard","sourceUrl":"https://www.npmjs.com/package/llm-trust-guard","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T05:21:22.124Z","isPublic":true,"metadata":{}},{"factKey":"protocols","label":"Protocol compatibility","value":"MCP, OpenClaw","category":"compatibility","href":"https://www.xpersona.co/api/v1/agents/npm-llm-trust-guard/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/npm-llm-trust-guard/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-15T05:21:22.124Z","isPublic":true,"metadata":{}},{"factKey":"handshake_status","label":"Handshake status","value":"UNKNOWN","category":"security","href":"https://www.xpersona.co/api/v1/agents/npm-llm-trust-guard/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/npm-llm-trust-guard/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true,"metadata":{}}],"highlights":["Trust evidence available"],"agentCard":{"name":"llm-trust-guard","description":"Comprehensive security guards for LLM-powered and agentic AI applications - 22 protection layers covering OWASP Top 10 for LLMs 2025, Agentic Applications 2026, and MCP Security. All guards now accessible via unified TrustGuard facade. Features prompt inj","source":"GITHUB_OPENCLEW","sourceId":"npm:llm-trust-guard","homepage":"https://www.npmjs.com/package/llm-trust-guard","repository":"https://github.com/nkratk/llm-trust-guard","documentation":"https://www.xpersona.co/agent/npm-llm-trust-guard","protocols":["MCP","OPENCLEW"],"capabilities":["llm","security","ai","agentic","prompt-injection","pap-attacks","persuasion-attacks","multimodal-injection","rag-security","embedding-attacks","memory-poisoning","rbac","multi-tenant","schema-validation","trust-architecture"],"languages":["typescript"],"install":{"command":"git clone https://github.com/nkratk/llm-trust-guard.git","ecosystem":"git"}}}