ai-influencer-strategy

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 (Manual longlist process and Manual vetting checklist) explicitly directs searching public social media (e.g., "Search relevant hashtags", "Review the top 20–30 posts", "Read the most recent 20 comments") and using third‑party tools like HypeAuditor/SocialBlade to inspect follower data, meaning the agent would ingest and act on untrusted user‑generated content from public websites.