writing-proofreading

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "信源查证" workflow (see SKILL.md Step 4 and references/source-verification.md) explicitly directs the agent to search for and cite public web sources (政府/媒体/个人博客/社交媒体) and to read/interpret those findings to verify claims and produce footnotes, so untrusted third‑party content can influence its next actions.