query
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (SAFE): No malicious instruction overrides or jailbreak attempts were detected in the skill instructions.
- [DATA_EXFILTRATION] (SAFE): The skill securely requires API keys to be set via environment variables rather than hardcoding them.
- [REMOTE_CODE_EXECUTION] (SAFE): No remote scripts are downloaded or executed; the skill relies entirely on pre-configured MCP tools.
- [INDIRECT_PROMPT_INJECTION] (LOW): 1. Ingestion points: External record content is ingested via the
search-recordstool. 2. Boundary markers: Absent from instructions. 3. Capability inventory: Limited to Pinecone index metadata and search operations. 4. Sanitization: No sanitization logic is defined for the content of retrieved records.
Audit Metadata