pp-hotel-goat

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

• Third-party content exposure detected (low risk: 0.10). The skill searches public hotel listings and reads property reviews from Google Hotels via CLI, which is third-party web content fetched at runtime.

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 an external CLI and MCP server via npm (@mvanhorn/printing-press-library) and Go (github.com/mvanhorn/printing-press-library/...), which are third-party repository locators acting as operational dependencies with weak or common/unofficial provenance.