02-url-to-explainer-video

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

• Third-party content exposure detected (medium risk: 0.30). The workflow’s runtime path explicitly fetches and reads arbitrary product page content provided by the requester (“URL input intake gate”), then extracts claims from that fetched free text before scriptwriting.

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

• Potentially malicious external URL detected (high risk: 0.90). The SKILL explicitly requires fetching and reading a user-supplied product page ("a single product URL") at runtime and then uses that page's extracted claims to drive the script-writing pipeline, so external page content directly controls the agent's outputs.