gh-image

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow reads existing PR/issue bodies via gh pr view --json body (lines 91, 103), which exposes the agent to outsider-authored comments and issue descriptions on GitHub repositories.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install and run a third-party GitHub CLI extension (drogers0/gh-image) from an unofficial personal GitHub repository (https://github.com/drogers0/gh-image), constituting an operational dependency with medium provenance.