software-copyright-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 workflow and helper scripts (scripts/fetch_web_evidence.py and scripts/_fetch_web_evidence.mjs) autonomously fetch and render arbitrary public/product URLs, extract page text/excerpts and screenshots into manifest.json and then use those artifacts in decision-making and document generation (export_ruanzhu_docx.py), so it clearly ingests untrusted third‑party web content that can influence agent actions.