git-pr-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes git and GitHub CLI (gh) commands to automate the PR process, including branching, committing, pushing, and merging.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted repository data (via git diff) to generate PR content and commit messages. 1. Ingestion points: Step 2 and 4 read file changes. 2. Boundary markers: No explicit boundaries or instructions to ignore embedded commands are present. 3. Capability inventory: git commit, git push, gh pr create, and gh pr merge. 4. Sanitization: No sanitization of code content is performed before analysis.
Audit Metadata