pp-google-business-profile

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to run the Google Business Profile CLI in --agent mode, which fetches live Google Business Profile data (outsider-authored content from the external service) and returns it as readable JSON on stdout for the agent to ingest into LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime install commands that fetch and execute remote code required by the skill — e.g., the npx installer @mvanhorn/printing-press-library (npx -y @mvanhorn/printing-press-library ...) and go install github.com/mvanhorn/printing-press-library/...@latest — so external content from those URLs would be fetched and run to satisfy the skill's dependency.