ecommerce-chuhaijiang-tiktok-live

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to api.nexscope.ai to retrieve commerce data. This is the primary function of the skill and targets the vendor's own API infrastructure.
  • [COMMAND_EXECUTION]: Standalone Python scripts are used to manage API requests and process response data. The scripts operate within the project directory using standard library functions.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: TikTok livestream data (e.g., titles, nicknames, product labels) is ingested from external API responses in the scripts folder.
  • Boundary markers: Instructions specify saving full responses to disk and returning only concise summaries to the agent context.
  • Capability inventory: The skill uses standard Python libraries for network communication and file system operations within the local workspace.
  • Sanitization: Request parameters are validated against schemas; API response data is handled as structured JSON.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:13 AM
Security Audit — agent-trust-hub — ecommerce-chuhaijiang-tiktok-live