github

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it retrieves data from external, potentially untrusted sources like GitHub issues, pull requests, and workflow logs.
  • Ingestion points: Data enters the agent context through 'gh pr view', 'gh issue list', and 'gh api' commands.
  • Boundary markers: No specific delimiters or 'ignore embedded instructions' prompts are present to prevent the agent from executing instructions found in external data.
  • Capability inventory: The skill has write capabilities, including merging pull requests and creating issues.
  • Sanitization: External content is not sanitized or filtered before being processed.
  • [EXTERNAL_DOWNLOADS]: The skill's metadata specifies the installation of the GitHub CLI tool.
  • It utilizes standard package managers like Homebrew ('brew') and APT ('apt') to install 'gh', which is a well-known tool from a trusted organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM