opc-community-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 (SKILL.md Step 1 "检索") together with references/search-queries.md and the research.md/output-format.md templates — and enforced by validate-research.sh which requires multiple source URLs — explicitly instruct the agent to collect and interpret content from public sites (e.g., mp.weixin.qq.com, xiaohongshu.com, gov.cn), meaning it ingests untrusted third‑party web content that can materially influence topic selection and article drafting.