screencast

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

• Third-party content exposure detected (low risk: 0.10). Source text exposure happens only to the page the user directs agent-browser record start to via the runtime URL argument, and the skill itself only ingests its own command text (e.g., screencast chapter / screencast note strings) rather than automatically reading outsider-authored free text from a social/web/ticket feed.