agentic-mermaid-diagram-workflow

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill features an execute tool designed to run JavaScript snippets to handle complex control flows that standard tools cannot express. Documentation in references/code-mode.md specifies that this code is executed within a node:vm sandbox environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes Mermaid source code which can include interaction syntax such as click events and callback functions. This presents an indirect prompt injection surface if the diagrams are rendered with loose security settings. The instructions in references/upstream/classDiagram.md and SKILL.md demonstrate and recommend using a strict security level to prevent unauthorized script execution.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill documents a 'hosted MCP' channel that communicates with https://agentic-mermaid.dev/mcp. This involves sending diagram source and custom execution code to a remote endpoint. The skill author responsibly advises users in references/hosted-mcp.md to prefer local channels (library, CLI, or stdio MCP) when working with sensitive data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 01:25 PM
Security Audit — agent-trust-hub — agentic-mermaid-diagram-workflow