ecommerce-tiktok-product-discovery

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script (scripts/tiktok_product_discovery.py) to handle API interactions, data caching, and result formatting.
  • [EXTERNAL_DOWNLOADS]: Fetches TikTok e-commerce data from the NexScope proxy API endpoint (/api/v1/tools/research/fastmoss/productSearch) using the urllib library.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests external product data (titles, descriptions, shop names) from the FastMoss API via the Python script's call_api function.
  • Boundary markers: None. The skill lacks explicit instructions to ignore or delimit potentially malicious instructions embedded in the API response data.
  • Capability inventory: The agent can execute the included Python script, which has permissions to perform network requests and write files to the local project directory (/nexscope/).
  • Sanitization: None. The script prints the raw or summarized JSON response directly to stdout, where it is consumed by the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:13 AM