clade-reference-architecture

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation and template resource. The provided code snippets are instructional examples for developers.
  • [EXTERNAL_DOWNLOADS]: The skill mentions the @modelcontextprotocol/sdk Node.js package. This is an official package from Anthropic for building MCP servers and is considered a safe, well-known dependency.
  • [COMMAND_EXECUTION]: The documentation describes the use of $ARGUMENTS in slash commands and hook configurations (e.g., pre-tool-call). These are standard platform features for building plugins and the examples provided (like echo) are benign.
  • [REMOTE_CODE_EXECUTION]: The MCP server example shows how to set up a tool provider. While this involves executing code, it is the intended purpose of the skill to teach how to build these providers, and the example itself is a safe scaffold.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 01:01 PM
Security Audit — agent-trust-hub — clade-reference-architecture