paw-mkt-influencer

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

• Third-party content exposure detected (high risk: 1.00). The skill's influencer-identification reference explicitly instructs the agent to use agent-browser to open and scrape public social sites (e.g., references/influencer-identification.md "Research Mode: Influencer Discovery" with agent-browser commands for TikTok, Instagram, and YouTube), meaning the agent will fetch and interpret untrusted, user-generated third‑party content that can materially influence vetting and campaign actions.