kolsprite-search

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill depends on an external Model Context Protocol (MCP) server at https://www.sellerspace.com/yunya_mcp/ for fetching TikTok data. This endpoint is a legitimate part of the service provided by the skill author and is necessary for its intended search functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests third-party data from TikTok profiles and content, presenting an indirect injection surface.\n
  • Ingestion points: Creator, product, and video data retrieved from the yunyamcp MCP tool.\n
  • Boundary markers: Not present; the instructions do not define delimiters for external content.\n
  • Capability inventory: The skill only supports read operations for TikTok data and does not have access to shell commands or file system writes.\n
  • Sanitization: Not present; no filtering or escaping of external content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 09:24 AM