webrtc-spec

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow (search, section, fetch, index) fetches and text-extracts outsider-authored free text from public W3C/IETF pages (e.g., urllib.request.urlopen of https://www.w3.org/TR/... and https://datatracker.ietf.org/doc/html/rfc...), then injects that extracted prose into the agent context via printed snippets/sections.