pr
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gitandgh(GitHub CLI) commands to perform branch management and pull request creation. These operations are limited to the user's local repository and the configured remote. - [PROMPT_INJECTION]: The skill ingests untrusted data from the local repository (commit messages and code diffs) to generate a summary. While it lacks explicit boundary markers, this is a standard risk for summarization tasks and does not pose a high threat given the tool's scope.
- Ingestion points: Git commit messages and code diffs read via
git logandgit diffin SKILL.md. - Boundary markers: Absent.
- Capability inventory: Branch pushing and PR creation via
git pushandgh pr createin SKILL.md. - Sanitization: Absent.
Audit Metadata