ship-it
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gitandgh(GitHub CLI) utilities to perform repository management tasks. These commands are executed locally based on the skill's defined workflow. - Evidence: Execution of
git commit,git push,gh pr create, andgh pr mergein steps 2, 3, and 5. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted data (file diffs) to generate natural language outputs (commit messages and PR descriptions).
- Ingestion points:
git statusandgit diffoutputs in Step 2. - Boundary markers: None present to delineate between code content and instructions.
- Capability inventory: High-impact capabilities including
git pushandgh pr merge(Step 3 and Step 5). - Sanitization: No explicit sanitization or validation of the diff content is performed before passing it to the LLM.
- [SAFE]: The skill's behavior is consistent with its stated purpose as a developer productivity tool. It uses authenticated standard interfaces (GitHub CLI) and includes user-confirmation steps for destructive actions like staging files.
Audit Metadata