mermaid-diagram
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
findutility to dynamically locate its installation directory and executes shell and Node.js scripts for maintenance and rendering. It also interpolates configuration values from a local JSON file into command-line arguments, which could pose a risk if the configuration file is untrusted. - [PROMPT_INJECTION]: The skill processes untrusted user input and file content to generate diagrams without using boundary markers or sanitization, creating an attack surface for indirect prompt injection. This includes loading specialist instructions from local files discovered at runtime.
- Ingestion points: User input ($ARGUMENTS) and external code files read for analysis.
- Boundary markers: None detected; external content is interpolated directly into processing prompts.
- Capability inventory: Access to
Bash(shell execution),Read(file access), andWrite(file creation) tools. - Sanitization: No validation or escaping of external content is performed before interpolation.
Audit Metadata