git-commit-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines workflows that involve executing bash commands such as
git log,git diff,npm test, andnpm run format:check. These commands are used to inspect the repository state and validate code quality within the local environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its reliance on parsing external data from git logs.
- Ingestion points: Untrusted data enters the agent context via
git logcommands which retrieve commit subjects and bodies from the repository history. - Boundary markers: The skill does not define or use specific boundary markers or delimiters to separate the ingested commit messages from the agent's internal instructions.
- Capability inventory: The skill is granted access to
Bash,Read, andGrep, which allows it to execute commands and read files based on the interpreted log data. - Sanitization: There is no evidence of sanitization, filtering, or validation logic to prevent the agent from acting on instructions embedded within commit messages.
Audit Metadata