deep-council

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns or safety violations were detected. The skill implements a robust orchestration workflow for multi-model reviews using modular bridge adapters and includes an adversarial debate stage to validate findings.
  • [EXTERNAL_DOWNLOADS]: The skill instructions provide guidance for manual installation of missing dependencies from the vendor's GitHub repository (github.com/mikeng-io/agent-skills). These resources are associated with the skill author's own suite and are documented as legitimate vendor resources.
  • [COMMAND_EXECUTION]: Utilizes restricted shell commands such as ls, which, cat, and mkdir to confirm the presence of dependencies, check for available CLI tools (Gemini, Codex, OpenCode), and manage local output directories.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:42 PM