meta-sentiment-analysis

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

• Third-party content exposure detected (high risk: 1.00). SKILL.md's required workflow explicitly instructs collecting and analysing public user-generated content (e.g., "Export or screenshot the last 100 comments, DMs, and mentions per platform" and manual searches on Facebook/Instagram/TikTok/YouTube and Google Alerts/Meta Business Suite) so the agent would read untrusted third‑party social/web content that can materially influence scoring and follow-up actions.