skills/akiojin/llmlb/gh-pr/Gen Agent Trust Hub

gh-pr

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes standard command-line tools (git, gh, jq) to interact with the local repository and GitHub. These operations are essential for the skill's primary function of PR management.
  • [DATA_EXFILTRATION] (SAFE): Network operations are restricted to communication with GitHub via the gh CLI and git fetch/push. No sensitive local files (e.g., SSH keys, AWS credentials) are accessed or transmitted.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes external data from GitHub (PR lists, commit SHAs).
  • Ingestion points: Data enters the skill via gh pr list and git rev-list.
  • Boundary markers: The skill uses jq to parse JSON output, providing structured handling of external data.
  • Capability inventory: Subprocess calls are limited to git and gh for repository management.
  • Sanitization: Use of quoted heredocs (<<'BODY') in the bash script prevents unexpected variable expansion when creating temporary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM