plan-with-team

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • Instructional Nature (SAFE): The skill consists entirely of Markdown instructions and templates. It defines roles and workflows for an AI agent team to collaboratively create planning documents.
  • Security-First Design (SAFE): The skill explicitly includes a 'The Skeptic' role whose sole mandate is to identify security holes, edge cases, and architectural flaws in the proposed designs, acting as a built-in safety check.
  • No Executable Code (SAFE): There are no scripts (Python, JS, Shell) included in the skill. All logic is contained within natural language instructions for the LLM.
  • Local Configuration Guidance (SAFE): The skill provides instructions for the user to enable experimental features in the Claude Code environment via .claude/settings.json. This is transparent configuration advice and does not involve automated or hidden system modifications.
  • Data Handling (SAFE): The skill processes user requirements to generate application plans. It does not access credentials, local files outside of its own resources, or non-whitelisted network domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 10:29 PM