gh-pr-check
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides and relies on a bash script that executes
git,gh(GitHub CLI), andjqto inspect repository state and PR metadata. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources that could potentially contain untrusted instructions, such as GitHub PR titles, URLs, and branch names.
- Ingestion points: Output of
gh pr listandgitbranch metadata retrieved in the bash script. - Boundary markers: None present in the instructions to separate external data from agent instructions.
- Capability inventory: The skill utilizes shell execution for git/gh/jq and performs network operations (fetch) against the remote repository.
- Sanitization: The provided bash script uses standard quoting for shell variables but does not perform explicit sanitization or filtering of PR titles or branch names before they are processed by the agent.
Audit Metadata