social-opinion-writer
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly requires "默认研究方式:自动联网补充公开信息" and Step 4 "联网搜集资料,写入 03-source-log.md" which instructs the agent to fetch and record public web sources/links (including media, reports, and potentially user-generated content as clues) and to read/interpret those sources as part of the drafting workflow, so third‑party content can materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata