manage-git
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes standard
gitcommands and a local linting tool (./vendor/bin/sail). The instructions explicitly mandate user confirmation for all commits and pushes, acting as a strong defense against accidental or malicious automated actions.\n- [INDIRECT_PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection through metadata it processes.\n - Ingestion points: Git commit messages, branch names, and file names provided by the user or derived from the repository environment (SKILL.md).\n
- Boundary markers: Absent; there are no delimiters or specific warnings to ignore instructions embedded in the processed data.\n
- Capability inventory: Command line execution via
gitand./vendor/bin/sail(SKILL.md).\n - Sanitization: Absent; the skill does not specify any validation or escaping of the input strings before they are interpolated into the shell commands.
Audit Metadata