skills/dagster-io/erk/gh/Gen Agent Trust Hub

gh

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill files. The skill focuses on providing legitimate instructions and reference material for the GitHub CLI (gh).
  • [PROMPT_INJECTION]: Indirect Prompt Injection attack surface identified, assessed as safe given the skill's primary purpose.
  • Ingestion points: The skill reads untrusted data from GitHub pull requests, issues, and comments via commands like gh pr view and gh issue list (documented in SKILL.md and references/gh.md).
  • Boundary markers: None specified; the agent is not explicitly instructed to use delimiters when processing external content.
  • Capability inventory: The skill uses the gh tool to perform repository mutations, API calls, and local branch management across its core scripts and reference files.
  • Sanitization: The skill does not provide instructions for sanitizing or validating data fetched from GitHub before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 03:21 AM