grill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project data including code, documentation, and glossaries, which constitutes an ingestion surface for indirect prompt injection.\n
- Ingestion points: Rule 2 instructs the agent to inspect relevant code, docs, glossary, and decisions.\n
- Boundary markers: The instructions do not define boundary markers or explicit commands to ignore embedded instructions within the ingested data.\n
- Capability inventory: The skill utilizes file-reading capabilities to inspect project files and file-writing capabilities to update plans and ADR documentation (Rule 6).\n
- Sanitization: There are no instructions for sanitizing or validating the content of external files before processing.
Audit Metadata