douyin-scraper-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill interfaces with vendor-owned API endpoints at api.scavio.dev. All network operations are directed to the vendor's infrastructure for the purpose of data retrieval as described in the skill metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from an external platform (Douyin), which presents a surface for indirect prompt injection. Malicious instructions could be embedded in user comments, video descriptions, or profile data.
  • Ingestion points: Data returned from all endpoints, particularly video comments, search results, and user profiles.
  • Boundary markers: The skill does not define specific delimiters (such as XML tags or unique markers) to isolate external data from the agent's instructions.
  • Capability inventory: The skill performs network operations via HTTP POST requests to fetch data.
  • Sanitization: No specific sanitization or filtering logic is defined for the content retrieved from the external source.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:23 PM
Security Audit — agent-trust-hub — douyin-scraper-api