douyin-content-surge

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to https://doubaoya.com to fetch video ranking data. This is the primary function of the skill and the destination is consistent with the vendor's documentation.
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/fetch_content_surge.py to perform the API requests. The script is transparent, well-documented, and does not use any dynamic code execution or external dependencies.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data (video titles and categories) from an external source.
  • Ingestion points: External data is ingested from the Doubaoya API response in fetch_content_surge.py.
  • Boundary markers: None are present in the skill instructions to separate the external content from the agent's logic.
  • Capability inventory: The skill has the capability to execute a specific local script and perform network requests to its API endpoint.
  • Sanitization: There is no explicit sanitization of the retrieved video metadata before it is formatted into tables for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 05:47 PM
Security Audit — agent-trust-hub — douyin-content-surge