clawteam

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the clawteam package from the Python Package Index (PyPI) and references official agent CLI tools from npm (e.g., Claude Code and Codex). These are standard dependencies required for the skill's documented functionality.
  • [COMMAND_EXECUTION]: The skill executes shell commands via the clawteam CLI to manage tmux sessions, create git worktrees, and spawn agent processes. These operations are central to its purpose of providing workspace isolation and parallel execution environments for AI agents.
  • [SAFE]: Analysis of the skill's scripts and instructions confirms they align with the stated goal of multi-agent orchestration. The skill uses local filesystem storage (~/.clawteam/) for state management and does not exhibit patterns of unauthorized data exfiltration, obfuscation, or persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:29 AM