tiktok-automation
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external TikTok profiles and video metadata (via tools like TIKTOK_LIST_VIDEOS and TIKTOK_GET_USER_PROFILE), which could theoretically contain adversarial instructions designed to influence the agent's behavior.
- Ingestion points: Data returned by listing and profile retrieval tools as described in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the agent when processing content from these external sources.
- Capability inventory: The skill possesses capabilities to modify external state, including publishing videos and posting photos (TIKTOK_PUBLISH_VIDEO, TIKTOK_POST_PHOTO).
- Sanitization: The instructions do not mention explicit sanitization or validation logic for the content fetched from the TikTok API.
- [EXTERNAL_DOWNLOADS]: The skill references and connects to an external MCP server at 'https://rube.app/mcp' to provide access to the TikTok automation toolkit from Composio.
Audit Metadata