gh

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill extensively uses the gh CLI to manage GitHub resources and git for read-only repository context.
  • [EXTERNAL_DOWNLOADS]: The skill documents the capability to install third-party GitHub CLI extensions using gh extension install.
  • [PROMPT_INJECTION]: The skill contains a risk surface for indirect prompt injection when processing content from pull requests, issues, or workflow logs.
  • Ingestion points: gh pr view, gh issue view, and gh run view --log in SKILL.md and references/jq-recipes.md.
  • Boundary markers: Absent; there are no instructions to the agent to disregard instructions found within the data it reads.
  • Capability inventory: High; includes merging pull requests, triggering workflows, and managing secrets.
  • Sanitization: Absent; data from GitHub is processed without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 02:46 AM
Security Audit — agent-trust-hub — gh