voice-ai-integration
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local bash scripts (
fetch-docs.shandfetch-doc-content.sh) to download documentation indices and content. These scripts are restricted to official vendor domains (doc.shengwang.cnanddoc-mcp.shengwang.cn) and are used solely for providing the agent with up-to-date integration guides. - [EXTERNAL_DOWNLOADS]: The skill references and provides instructions for downloading official tools and documentation from trusted sources, including the
AgoraIOGitHub organization and Shengwang's own documentation portals. These downloads are standard for the skill's intended purpose of SDK integration. - [CREDENTIALS_UNSAFE]: While the skill handles sensitive information such as App IDs and Customer Secrets, the documentation explicitly instructs users to manage these via environment variables and provides warnings against hardcoding secrets or committing them to version control, following security best practices.
- [DATA_EXFILTRATION]: Network operations are limited to fetching documentation from the vendor's infrastructure. There is no evidence of unauthorized data transmission or harvesting of user credentials.
Audit Metadata