find-bugs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git diffandgh repo viewto fetch repository information and branch changes for analysis. These commands are necessary for the primary function of auditing code changes. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from git diffs and local files, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill reads external content via
git diffand direct file reads in SKILL.md. - Boundary markers: None are explicitly defined to separate untrusted code content from agent instructions.
- Capability inventory: The skill is restricted to read operations and does not possess capabilities for file writing or outbound network requests beyond repository metadata retrieval.
- Sanitization: No sanitization or escaping is performed on the ingested code content.
Audit Metadata