tiktok-account-audit

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

• Third-party content exposure detected (medium risk: 0.30). The workflow collects public TikTok profile/video pages and third-party KOLSprite MCP data (creator search, video search, and caption extraction), which expose the agent to untrusted external creator-authored content and captions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The agent configuration file defines an external streaming HTTP MCP tool dependency at https://mcp.kolsprite.com/mcp which acts as an operational runtime dependency for data retrieval and search enrichment.