qmd

Warn

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill initiates the download of a CLI tool from a personal GitHub repository (https://github.com/tobi/qmd) and notes that GGUF models are automatically fetched from remote sources during the first run.
  • [REMOTE_CODE_EXECUTION]: The installation process uses bun install -g with a remote Git URL, which involves downloading and executing unverified code from an external source on the user's system.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a variety of shell commands to manage document collections and perform searches. It also includes specific instructions for establishing persistence through system cron jobs to automate indexing updates.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 18, 2026, 01:02 AM
Security Audit — agent-trust-hub — qmd