editorial-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md (Layer 4: Factual Accuracy) and references/fact-checking.md explicitly instruct "When web access is available, verify key claims using search tools" and to trace claims to primary sources on public websites, so the agent will fetch and read open third‑party web content (public sites/search results) that can materially influence its verification decisions.