codepatrol-triage
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from security investigation reports which are external sources that could contain untrusted content.\n
- Ingestion points: The skill reads security reports from a hub page as specified in the instructions.\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded instructions within reports are provided to the agent.\n
- Capability inventory: The skill creates and edits pages on the Cosense platform via the cosense skill.\n
- Sanitization: The skill does not describe any sanitization or filtering of external report content before it is processed and formatted.
Audit Metadata