save-md

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and saves external web pages, documents, and articles specified by the user via URLs or attachments, exposing the agent to arbitrary outsider-authored free text upon fetching.

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 invoke the third-party Firecrawl API endpoint at https://api.firecrawl.dev/v2/scrape via curl for fetching content when an opt-in fallback reader is used, constituting an unverified external runtime dependency with common/reputable unofficial provenance.