dmux-workflows

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing a local orchestration script (node scripts/orchestrate-worktrees.js) that processes a JSON configuration file. This script dynamically assembles and executes shell commands defined in a launcherCommand template to manage parallel agent sessions in tmux panes.
  • [EXTERNAL_DOWNLOADS]: The documentation references an external GitHub repository (github.com/standardagents/dmux) for installing the dmux utility, which is a dependency for the described workflows.
  • [PROMPT_INJECTION]: The orchestration workflow represents an indirect injection surface as it ingests task definitions and command templates from a plan.json file.
  • Ingestion points: plan.json file containing worker tasks and launcher commands.
  • Capability inventory: Shell command execution via node/bash, tmux pane management, and git worktree operations.
  • Boundary markers: None specified in the documentation for isolating task content within the generated task.md files.
  • Sanitization: No explicit sanitization or validation is mentioned for the command templates or worker task descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:41 AM
Security Audit — agent-trust-hub — dmux-workflows