x-post-extractor

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

• Third-party content exposure detected (high risk: 0.70). The skill's required Phase 4 "Fetch Media (Automatic)" explicitly runs capture_screenshot.py on "any URLs mentioned" and fetch_logos.py on domains, so it automatically fetches arbitrary public websites/domains referenced in transcripts (untrusted third‑party content) as part of its mandatory workflow, which could enable indirect prompt injection via fetched content.