git-workflow
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute a variety of shell commands to manage and inspect the local repository environment.
- Evidence: Use of
git log,git remote,gh repo view,ls -la,cat, andnpm versionacross various workflow steps. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the repository's files and history without sanitization.
- Ingestion points: The skill explicitly instructs the agent to read
CONTRIBUTING.md,.github/pull_request_template.md, and the output ofgit log --oneline(which contains user-provided commit messages). - Boundary markers: No delimiters or "ignore embedded instructions" warnings are provided when processing these external inputs.
- Capability inventory: The skill has extensive capabilities including file system access (
ls,cat), repository manipulation (git), and package management interactions (npm). - Sanitization: No evidence of validation or sanitization of the content read from files or logs before it is processed by the agent.
Audit Metadata