skill-workflow-creator

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional Markdown files and reference documentation. It does not contain any executable scripts, automated tool calls, or network operations.
  • [SAFE]: The content proactively addresses security risks, explicitly warning against 'permission sprawl' and recommending a 'deny-all' approach to tool access for subagents.
  • [SAFE]: Instructions for creating subagents emphasize the use of pure XML structures and strong modal verbs (MUST, NEVER, ALWAYS) to define clear boundaries and prevent unintended behaviors.
  • [SAFE]: The execution model described correctly identifies that subagents run in isolated contexts and prevents them from using interactive tools like AskUserQuestion, which reduces the risk of social engineering or prompt-based manipulation of the user.
  • [SAFE]: No obfuscation, hardcoded credentials, or suspicious external dependencies were found in any of the analyzed reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:05 AM
Security Audit — agent-trust-hub — skill-workflow-creator