github-pull-request
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard
gitandgh(GitHub CLI) commands to manage branches, view code changes, push to remotes, and create pull requests. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of repository data.
- Ingestion points: The agent reads untrusted data from the repository via
git diffandgit status(SKILL.md). - Boundary markers: The prompt lacks specific instructions or delimiters to isolate the code diff content from the agent's instruction processing logic.
- Capability inventory: The skill possesses the ability to write to the remote repository (
git push) and create pull requests (gh pr create) (SKILL.md). - Sanitization: No sanitization or filtering is applied to the content retrieved from git diffs before it is used to populate the PR body.
Audit Metadata