grill
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to automatically gather facts from the environment (filesystem and tools) to populate its design tree and answer 'frontier' questions.
- Ingestion points: Instructions in
SKILL.mddirect the agent to 'look up' facts from the filesystem or tools directly when needed. - Boundary markers: The instructions do not define specific delimiters or guardrails for data retrieved from the environment.
- Capability inventory: The skill utilizes the
/executecommand to carry out code changes and recommends creating/modifying tickets in an external issue tracker. - Sanitization: There are no explicit instructions to sanitize or escape data retrieved from the environment before it is interpolated into the design tree or used to propose code changes.
Audit Metadata