git-hygiene
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled shell script (
git-hygiene.sh) and uses standard Git and GitHub CLI (gh) commands to perform operations such as repository inventory, branch deletion, and worktree removal. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it ingests and interprets data from external, untrusted sources including Git commit messages, diffs, and GitHub PR metadata to make decisions about code redundancy and PR creation.
- Ingestion points: The agent reads output from
git log,git diff,gh pr list, andgh pr view(specifically referenced in SKILL.md sections 4.5 and 4.6). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat ingested Git/PR metadata as data only and to ignore any embedded instructions.
- Capability inventory: The skill possesses significant local capabilities including executing shell scripts, modifying Git repository state (pull, checkout, rebase, branch/worktree deletion), and performing network operations via the GitHub CLI.
- Sanitization: The instructions do not include steps for sanitizing or validating the content of commit messages or PR descriptions before they are processed by the agent.
Audit Metadata