NYC

Dispatching Parallel Agents

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • [Metadata] (LOW): The skill originates from a source repository (github.com/bobmatnyc/claude-mpm-skills) that is not on the pre-approved trusted source list. While no malicious behavior was identified, users should generally verify third-party repositories before use.
  • [Indirect Prompt Injection] (INFO): The skill outlines a workflow for spawning sub-agents based on system state (e.g., test failures). This introduces a surface where malformed test outputs or file names could influence the tasks assigned to sub-agents. However, the skill explicitly includes mitigation steps such as 'Conscious Integration' and 'Review and Integrate' to ensure human/agent oversight of all changes.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 09:55 PM