content-repurposer

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 0 intake explicitly asks the user to "Paste the content OR share the URL (blog post, LinkedIn article, transcript, etc.)" and Phase 1 requires extracting the core thesis and supporting points from that source, so the agent would ingest and act on untrusted public third‑party content (web posts/transcripts) as part of its workflow.