skills/dakdevs/skills/pr-this/Gen Agent Trust Hub

pr-this

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements a security best practice by identifying 'questionable files' (such as .env or credentials) and requiring user confirmation before staging them for commit.
  • [COMMAND_EXECUTION]: Uses standard Git and GitHub CLI commands to manage the PR lifecycle. The commands are well-structured and use heredocs to safely handle multi-line content.
  • [PROMPT_INJECTION]: The skill has an indirect injection surface because it processes untrusted code diffs.
  • Ingestion points: git diff main...HEAD and git log in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: git add, git commit, git push, gh pr create/edit in SKILL.md.
  • Sanitization: Manual user review of staged files in Step 0.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 07:00 PM
Security Audit — agent-trust-hub — pr-this