pp-judge-me

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

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to interact with the Judge.me REST API via CLI commands (such as fetching reviews and moderation queues), which ingest user-generated product reviews containing outsider-authored free text.

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 a CLI tool via npx from @mvanhorn/printing-press-library or compile/install Go code directly from github.com/mvanhorn/printing-press-library/..., which constitutes an unofficial external operational dependency.