drill
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository to facilitate design reviews. 1. Ingestion points: Reads project code, documentation (CONTEXT.md, CONTEXT-MAP.md, ADRs), and commit history as described in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided when reading files. 3. Capability inventory: The skill can write files to the repository (docs/specs/, CONTEXT.md, docs/adr/) and trigger other tools or skills (research, prototype, implement). 4. Sanitization: No sanitization of the ingested codebase content is performed before processing.
- [SAFE]: All other analyzed behaviors, including file access and tool invocation, are consistent with the skill's stated purpose of project planning and design review.
Audit Metadata