sus-campaign
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project ledgers (e.g., issues, epics). While this constitutes an attack surface, the instructions emphasize isolation, deterministic local verification, and human oversight to mitigate potential risks.
- [DATA_EXPOSURE_AND_EXFILTRATION]: Artifact storage is directed to a specific agent-related directory (~/.agents/artifacts/). No evidence of unauthorized file access or external data exfiltration was found.
Audit Metadata