influencer-outreach

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 ("Xiaohongshu Search", "Hashtag search", "Browse relevant categories" and "Manual Discovery") explicitly instructs ingesting and reviewing public, user-generated Xiaohongshu posts and competitor posts so the agent reads that third‑party content to choose targets and craft outreach, creating exposure to indirect prompt injection.