search-term-miner
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external search-term reports (CSV or pasted text). It includes specific security instructions for the agent to treat these files as untrusted and to disregard any instructions embedded within the data, which is a recommended safety measure for this type of operation.
- [DATA_EXPOSURE]: The skill operates on search-term data provided by the user and writes analysis results to a local memory directory within the agent's environment. No patterns of sensitive file access or unauthorized data exfiltration were detected.
Audit Metadata