douyin-scraper-api
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process large amounts of untrusted, user-generated content from Douyin, including video comments, user profiles, and hashtag descriptions.
- Ingestion points: External data enters the agent context via multiple endpoints such as
/api/v1/douyin/video/commentsand/api/v1/douyin/user/profilelocated inSKILL.md. - Boundary markers: The instructions lack explicit technical delimiters or specific "ignore instructions within data" warnings to prevent the agent from potentially following malicious commands hidden in social media comments or profile bios.
- Capability inventory: The skill facilitates network operations to the scraper API and allows the agent to resolve share links, which could be used as part of a multi-step injection chain.
- Sanitization: There are no documented steps for sanitizing, filtering, or escaping the external content retrieved from the API before it is presented to the agent's context.
Audit Metadata