prkit
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git log and git diff to generate pull request titles and bodies. This creates a surface for indirect instructions to influence agent output. 1. Ingestion points: git log, git diff, docs/verify/proof.md, and .github/pull_request_template.md. 2. Boundary markers: Absent. 3. Capability inventory: git push, gh pr create, gh pr edit, gh issue edit, and gh stack submit. 4. Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill executes multiple shell commands using git and gh CLI to automate PR workflows and issue tracking, which are the primary functions of the tool.
Audit Metadata