douyin-research
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and analyze external data from Douyin, creating a surface for indirect instructions.
- Ingestion points: Data retrieved from Douyin via tools like
douyin_search_general_search_v2anddouyin_search_video_search_v2as listed inSKILL.md. - Boundary markers: The skill instructions do not provide specific delimiters or ignore-instructions for the agent when processing external content.
- Capability inventory: The skill lacks dangerous capabilities such as file writing or code execution; it is restricted to search and analysis.
- Sanitization: No explicit sanitization or filtering of Douyin data is mentioned in the skill files.
Audit Metadata