github-pr

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs legitimate repository management tasks using the official GitHub CLI (gh). Access to local Git logs and repository labels is standard for PR automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local Git commit history to generate PR metadata.
  • Ingestion points: The skill reads commit history in SKILL.md using git log to summarize changes.
  • Boundary markers: Absent; the instructions do not define specific delimiters for separating commit content from the PR template.
  • Capability inventory: Executes shell commands including gh auth status, gh label list, and gh pr create in SKILL.md.
  • Sanitization: Absent; the agent is expected to interpret and format the text before passing it as arguments to the CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:50 PM
Security Audit — agent-trust-hub — github-pr