work-review
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands like
git diff,wc, andgrepto perform static code analysis and calculate codebase metrics. - [COMMAND_EXECUTION]: The skill executes user-provided or project-defined build, typecheck, and test scripts (Step 0) as part of its deterministic verification process.
- [PROMPT_INJECTION]: The skill processes untrusted code content from the repository, presenting a surface for indirect prompt injection. This is inherent to the tool's primary purpose.
- Ingestion points: Code changes and file contents accessed via
gitandgrepin SKILL.md. - Boundary markers: The skill does not define explicit delimiters to isolate ingested code content from its internal instructions.
- Capability inventory: Shell command execution (git, wc, grep) and the ability to trigger project scripts.
- Sanitization: No evidence of content sanitization or filtering against embedded instructions is provided.
Audit Metadata