url-to-markdown

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

• Third-party content exposure detected (low risk: 0.10). The agent fetches arbitrary public web pages via URL extraction, meaning outsider-authored content is retrieved only when explicitly targeted by a search or link.

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 fetch external content from an arbitrary third-party endpoint (md.replynodes.com) to use as source text, which constitutes an unofficial external operational dependency.