commit-push-pr
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses pre-computed context placeholders (
!git ...) inSKILL.mdandindex.mdto gather repository metadata like the current branch name and status. These are legitimate, read-only Git operations used for developer workflows. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository via Git commands.
- Ingestion points: Repository state and file diffs are read using
git statusandgit diffas described in the workflow sections. - Boundary markers: No explicit delimiters are specified for the diff content.
- Capability inventory: The skill performs repository writes (
git commit), remote pushes (git push), and creates external pull requests (gh pr create). - Sanitization: The skill relies on manual review by instructing the agent to ensure no sensitive files are staged.
- [COMMAND_EXECUTION]: The skill executes standard CLI tools (
git,gh,ruff,pytest) to perform its primary function of code management and quality assurance.
Audit Metadata