pp-thelancet

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and retrieves Lancet academic articles from OpenAlex via a local CLI, representing fetched third-party publication metadata and abstracts that constitute active search/fetch of external content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of external tools via npm and Go packages hosted on GitHub (github.com/mvanhorn/printing-press-library), which constitutes an unverified third-party operational dependency.