tiktok-automation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted metadata from TikTok (titles, profiles) which could contain hidden instructions.
- Ingestion points: TIKTOK_LIST_VIDEOS and TIKTOK_GET_USER_PROFILE.
- Boundary markers: Absent; instructions do not specify delimiters for external content.
- Capability inventory: TIKTOK_PUBLISH_VIDEO and TIKTOK_POST_PHOTO (write operations).
- Sanitization: Absent; no validation of TikTok-sourced strings is described.
- [External Downloads] (LOW): The skill requires connecting to an external MCP server at https://rube.app/mcp. This endpoint is not on the trusted sources list, but the severity is lowered as it is the primary mechanism for the skill's intended functionality.
Audit Metadata