firecrawl

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

• Third-party content exposure detected (low risk: 0.10). The skill scrapes and crawls arbitrary web pages using Firecrawl, exposing the agent to outsider-authored free text from fetched websites.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs execution of an external npm package (@useclawlink/cli) from a third-party domain (claw-link.dev), which constitutes an unofficial operational dependency.