lwy-llm-wiki
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or unauthorized remote code execution were detected. The skill operates primarily on a local directory to maintain a compounding knowledge base.
- [COMMAND_EXECUTION]: The skill uses Node.js scripts and local CLI tools (like sqlite3 and lark-context) to perform wiki maintenance and data ingestion tasks. It also modifies IDE configuration files in the user's home directory to register its automated hooks, which is a documented and intended behavior.
- [EXTERNAL_DOWNLOADS]: The skill identifies a dependency on the @tiktok-fe/lark-context package for users who wish to use the optional Feishu integration features.
Audit Metadata