article-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Phase 2 "Research (Web Search)" and associated sources.json/research_templates explicitly instruct the agent to search, fetch and record external URLs (e.g., laravel.com, blogs, GitHub) and then use those sources to shape drafts and companion projects, so untrusted third‑party content is ingested and can influence actions.