coo
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for operational assistance and utilizes standard tools like WebSearch, WebFetch, Write, Edit, and Read for their documented purposes. All actions are scoped to relevant project directories and standard research tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its interaction with untrusted data sources.\n
- Ingestion points: The skill scans local files in
docs/operations/and retrieves external content viaWebSearchandWebFetch.\n - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the processed data.\n
- Capability inventory: The agent can write to
docs/operations/and modifyHUMAN_AGENDA.md.\n - Sanitization: No sanitization or validation of the input data is specified.
Audit Metadata