flyingnobita-deliver-review
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository diffs and branch contents which may contain untrusted data during the review and repair loop.
- Ingestion points: Reads target branch HEAD, fixed-point SHAs, and repository diffs from the file system (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted branch content from the agent's instructions.
- Capability inventory: Manages git worktrees, writes artifacts to the filesystem, and executes repository commits (SKILL.md).
- Sanitization: The instructions do not describe sanitization or filtering logic for the ingested repository data.
Audit Metadata