anygen-doc
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (
scripts/anygen.py) and standard system tools likecurlto manage document generation tasks and provide results to the user via background subagents. - [EXTERNAL_DOWNLOADS]: It interacts with legitimate external endpoints including the vendor's domain (
www.anygen.io) and the well-known Feishu/Lark API (open.feishu.cn) to facilitate document processing and user communication. - [CREDENTIALS_UNSAFE]: The skill manages authentication tokens securely by supporting environment variables and local configuration files with restricted permissions (
chmod 600), preventing unauthorized access to the AnyGen API key. - [DATA_EXFILTRATION]: User-provided files are uploaded to the AnyGen service for processing. This behavior is restricted to files explicitly specified by the user and is central to the skill's primary documented purpose.
Audit Metadata