Skills
skills/magnusrodseth/dotfiles/github-cli/Gen Agent Trust Hub

github-cli

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): High-risk attack surface combining untrusted data ingestion with powerful write capabilities.
  • Ingestion points: SKILL.md uses gh issue view, gh pr view, and gh pr diff to pull external text into the agent context.
  • Boundary markers: Absent; no instructions provided to treat external output as untrusted or to use delimiters.
  • Capability inventory: SKILL.md provides tools for gh pr merge, gh pr edit, gh issue edit, and git push.
  • Sanitization: Absent; content from the GitHub API is processed without validation or filtering.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:35 PM