douyin-kol-search
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Douyin profiles which could contain adversarial content.
- Ingestion points: Data returned from the API in
scripts/run.pyincludes account nicknames and descriptions from the Douyin platform. - Boundary markers: There are no clear boundaries or warnings to the agent to disregard instructions potentially hidden in the retrieved influencer data.
- Capability inventory: The agent interacts with the structured data but could be misled by malicious content within the text fields of the KOL profiles.
- Sanitization: The skill does not perform sanitization on the external content before it is processed by the AI agent.
Audit Metadata