keyapi-tiktok-influencer-discovery

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls KeyAPI MCP tools (e.g., search_influencers, get_influencer_videos, get_influencer_followers) against https://mcp.keyapi.ai to ingest public TikTok user-generated data (profiles, videos, follower lists) and then reads and synthesizes those results into reports and decisions as described in SKILL.md and scripts/run.js, enabling untrusted third-party content to influence the agent's actions.