{"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","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"],"protocols":["MCP","OPENCLAW"],"safetyScore":77,"overallRank":37.2,"trustScore":null,"trust":null,"source":"GITHUB_OPENCLEW","updatedAt":"2026-04-15T05:21:22.124Z"}