sentiment-monitor

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md and references/platform-guide.md) explicitly instructs using opencli to fetch comments and posts from public, user-generated sources (微博/知乎/B站/小红书/抖音) and references/analysis-guide.md shows an LLM prompt that ingests those comments for labeling and report construction, meaning untrusted third‑party content is read and can materially influence subsequent analysis and actions.