story-origin-check

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime workflow (news-search + WebFetch of supplied evidence URLs and inspection of visible article text/metadata) can ingest outsider-authored free text from fetched web pages (e.g., third-party news articles or other outlets) into the agent’s LLM context via the fetched page content.