orchestrating-swarms

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as repository files, tool outputs, and findings from other agents. It includes robust defensive instructions requiring agents to treat this content as data only and specifically ignore any instruction-like text embedded within it.
  • [EXTERNAL_DOWNLOADS]: The documentation suggests installing the it2 utility, a well-known tool for iTerm2 integration, using standard package managers like uv, pipx, or pip.
  • [COMMAND_EXECUTION]: The orchestration patterns rely on standard system utilities such as git, grep, jq, and tmux for repository management, data filtering, and managing multi-agent execution environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 03:31 PM
Security Audit — agent-trust-hub — orchestrating-swarms