jb-committer
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes uncommitted code changes in the repository, which constitutes an indirect prompt injection surface if those changes contain adversarial instructions.
- Ingestion points: Local git working directory content accessed via git status and diff commands.
- Boundary markers: No specific delimiters or safety instructions are used to distinguish file content from agent logic.
- Capability inventory: Execution of git commit and git push commands to local and remote repositories.
- Sanitization: No validation or sanitization of the file content is performed before processing.
Audit Metadata