board-meeting
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external memory files, which represents an attack surface for indirect prompt injection if those files are tampered with.
- Ingestion points: In Phase 1, the skill loads content from
memory/company-context.mdandmemory/board-meetings/decisions.md. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate the ingested data from the system prompt.
- Capability inventory: The skill is authorized to read and write files within the
memory/directory but lacks network exfiltration or shell execution capabilities. - Sanitization: There is no evidence of sanitization, filtering, or schema validation for the data loaded from the memory files.
Audit Metadata