knowledge-searching
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions to override agent behavior or bypass filters were detected.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or unauthorized data access patterns were found.
- [Indirect Prompt Injection] (SAFE): The skill processes external documentation as part of its primary purpose. Although boundary markers are absent, the restricted capability set (RAG only) minimizes risk. Evidence: 1. Ingestion points: rag_search_knowledge_base, rag_search_code_examples; 2. Boundary markers: Absent; 3. Capability inventory: RAG functions only; 4. Sanitization: Absent.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external code dependencies or remote script execution patterns were identified.
Audit Metadata