skills/madflojo/dotfiles/open-pr/Gen Agent Trust Hub

open-pr

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh CLI commands to perform its primary function. This includes commands like git remote -v, git rev-parse, git log, and gh pr create.
  • [DATA_EXFILTRATION]: The skill reads repository information (remotes, branch names, commit logs, and diff stats) and transmits this information to GitHub via the gh command. This behavior is consistent with the skill's documented purpose of creating pull requests.
  • [SAFE]: The skill demonstrates defensive coding practices by specifically instructing the agent to use heredocs (<<'EOF') and stdin (--body-file -) when creating the PR body. This technique prevents potential shell injection or history expansion issues (such as with the ! character) that could occur if user-controlled content were passed as direct command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:44 AM
Security Audit — agent-trust-hub — open-pr