project-coordination
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface in its workflow for processing project documentation.\n
- Ingestion points: Untrusted data is ingested from
docs/product/review-notes/*.mdanddocs/product/design/*.md.\n - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the ingested files.\n
- Capability inventory: The skill is capable of writing to
docs/product/project-plan.mdand thedocs/product/status-reports/directory.\n - Sanitization: No sanitization, escaping, or validation of the external markdown content is performed before processing.
Audit Metadata