grill
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from diffs and possesses the ability to write to the repository, creating a standard surface for indirect prompt injection.
- Ingestion points: Reads from working trees, branches, and pull requests as described in Step 1 of SKILL.md.
- Boundary markers: The instructions lack explicit delimitation markers to separate user-provided diff data from the agent's core instructions.
- Capability inventory: The skill can modify source code, add rationale to commits/PRs, and restructure code for clarity (SKILL.md).
- Sanitization: No mechanisms for sanitizing or escaping the content within the diffs are defined.
Audit Metadata