pull-request

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (gh) for several operations including listing issues (gh issue list), viewing issue details (gh issue view), verifying pull request authors (gh pr view), and merging pull requests (gh pr merge). These commands are standard for the skill's intended purpose of managing GitHub PRs.
  • [COMMAND_EXECUTION]: Provides guidance on using the --admin flag with gh pr merge to bypass branch protections. This is a legitimate feature of the GitHub CLI intended for authorized administrative actions.
  • [PROMPT_INJECTION]: The skill processes data from external sources, specifically GitHub issues and pull request content, which could contain adversarial instructions.
  • Ingestion points: Data is ingested via gh issue view and gh pr view commands in references/github-pr-operations.md.
  • Boundary markers: The instructions do not specify explicit boundary markers or delimiters for the ingested issue/PR content.
  • Capability inventory: The skill has the capability to execute shell commands via the gh CLI (merge, list, view) and write text to PR descriptions.
  • Sanitization: There are no explicit sanitization or filtering steps mentioned for the ingested GitHub data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 06:15 PM
Security Audit — agent-trust-hub — pull-request