byted-data-search

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements its core functionality through several Python scripts located in the scripts/ directory. These scripts are designed to be executed by the agent to fetch metadata, query data sources, and discover field enumerations.
  • [EXTERNAL_DOWNLOADS]: The scripts make outbound network requests to https://sd6k08f59gqcea6qe13vg.apigateway-cn-beijing.volceapi.com/mcp using the requests library. This is a legitimate endpoint for Volcengine (ByteDance's cloud platform) and is used to communicate with the Model Context Protocol (MCP) gateway to retrieve industry data.
  • [CREDENTIALS_UNSAFE]: The skill requires authentication via VOLCENGINE_ACCESS_KEY and VOLCENGINE_SECRET_KEY. The implementation correctly instructs users to store these in environment variables and transmits them securely via HTTPS headers to the official vendor gateway. No hardcoded secrets were found.
  • [SAFE]: All identified external resources, including the API gateway and the required credentials, are part of the official ByteDance/Volcengine infrastructure. The skill's behavior is consistent with its stated purpose of providing industry data analysis tools, and no malicious patterns such as obfuscation or persistence were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 02:40 AM