find-bugs
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted code diffs, which creates an entry point for potential indirect prompt injection.
- Ingestion points: Git diff output and file contents accessed during Phase 1.
- Boundary markers: The instructions lack explicit delimitation or warnings to treat the processed code content as non-executable data.
- Capability inventory: The agent is permitted to read local files and branch history. No network access or file-writing capabilities are authorized.
- Sanitization: No sanitization or escaping mechanisms are defined for the processed diff data before the agent analyzes it.
Audit Metadata