pr
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local git and GitHub CLI commands to automate the pull request process. Evidence: Commands such as git branch, git status, git log, git diff, git push, and gh pr are called within the SKILL.md file.
- [DATA_EXFILTRATION]: Repository metadata and code summaries are transmitted to GitHub's platform as part of the tool's intended functionality. Evidence: Branch names and commit histories are sent to GitHub's servers via the gh CLI tool.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through repository history. Ingestion points: The outputs of git log main..HEAD and git diff main...HEAD are included in the agent's context in SKILL.md. Boundary markers: Absent. No specific delimiters or instructions are used to prevent the agent from obeying instructions embedded in commit messages. Capability inventory: The skill can push code (git push) and create or edit pull requests (gh pr create/edit). Sanitization: Absent. The skill does not filter or validate the content of commit messages or diffs before processing them.
Audit Metadata