gm-unknowns
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from 'PRD rows' to identify 'unknowns'.\n
- Ingestion points: The skill ingests data from the
rowID and the associated content in the PRD row.\n - Boundary markers: The skill does not define specific boundaries or use markers to ignore instructions potentially embedded within the data it processes.\n
- Capability inventory: The skill has the capability to write to the local file system (using the
mutable-addtool to write to.gm/receipts/) and invoke subsequent skills (gm-edit,gm-eliminate).\n - Sanitization: There is no evidence of input validation, escaping, or sanitization for the data being processed from the PRD row.
Audit Metadata