create-pull-request
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from untrusted repository content.
- Ingestion points: The skill reads and processes the output of
git logandgit diff, and it searches for and reads pull request templates from various locations (e.g.,.github/pull_request_template.md). - Boundary markers: No markers are used to isolate untrusted data from the agent's core instructions.
- Capability inventory: The skill has the capability to perform write operations including
git pushandgh pr create. - Sanitization: No sanitization or filtering is applied to the content extracted from commit messages or templates before it is used to generate the PR metadata.
- [COMMAND_EXECUTION]: The skill uses
gitandgh(GitHub CLI) for repository management and PR creation. While these are high-privilege tools, the skill incorporates safety rules such as "NEVER force push to main/master" and "NEVER push without user confirmation if already on main/master" to mitigate the risk of repository corruption.
Audit Metadata