gbrain-lite
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to manage a local directory of markdown files for knowledge storage. No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected.
- [COMMAND_EXECUTION]: The skill uses standard search utilities (ripgrep, grep) to perform full-text searches within the local 'brain/' directory. This is a legitimate use of command-line tools for knowledge management.
- [DATA_EXFILTRATION]: The skill operates strictly on a local workspace and does not initiate any network connections or access sensitive system paths (e.g., credentials or SSH keys). External references to GitHub or Hacker News items are treated as identifiers for deduplication, not as targets for unauthorized data transfer.
- [EXTERNAL_DOWNLOADS]: No external scripts, packages, or code execution patterns from remote sources were found. The skill relies on locally available tools and user-provided conversational data.
Audit Metadata