mega-code-login

Warn

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses uv run to execute a Python module. The working directory for this execution is dynamically determined by reading a path from ~/.local/share/mega-code/plugin-root, which introduces a dependency on the integrity of that local file.\n- [CREDENTIALS_UNSAFE]: Sensitive API credentials are stored in and retrieved from ~/.local/share/mega-code/.env. While the skill masks the API key in its verification output, it involves direct manipulation of secret-bearing files.\n- [COMMAND_EXECUTION]: The skill uses shell commands like cat, grep, and sed to manage configuration and verify stored credentials.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 20, 2026, 02:30 AM