ship-it
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute various Git commands (fetch, merge, push) and the GitHub CLI (gh pr create) to automate development workflows.
- [PROMPT_INJECTION]: The skill ingests untrusted data from the repository's environment, including branch names, commit messages, and the delivery-plan.md file, which are then interpolated into shell commands and pull request templates.
- Ingestion points: Data is sourced from
git branch,git log, and the contents ofdelivery-plan.md(Step 0 and Step 6). - Boundary markers: The skill lacks explicit delimiters or escaping mechanisms when using branch names in shell command substitutions, such as
git push origin $_BRANCH. - Capability inventory: The skill has permissions to use the
Bashtool, allowing it to perform file system operations and network communication via Git. - Sanitization: There is no evidence of validation or sanitization of repository-sourced metadata before it is used in automated command execution or PR generation.
Audit Metadata