douyin
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). This skill’s required workflow is to call TikHub endpoints (e.g., Douyin search/video/user/comments) at runtime, which returns outsider-authored free text (video captions/comments/user bios) that the agent would ingest into the LLM context for downstream analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata