agent-tutor-visualize

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided learning notes and concepts to create visual explanations, which constitutes a potential attack surface.
  • Ingestion points: User-supplied learning notes and concepts.
  • Boundary markers: No specific delimiters or 'ignore' instructions are provided for processed data.
  • Capability inventory: File system write operations for SVG files and potential tool execution (mermaid_lint, svg_save).
  • Sanitization: The skill mandates security requirements for SVG creation, such as prohibiting tags and remote URLs.
  • [COMMAND_EXECUTION]: The skill references the use of optional local tools for syntax validation and file management.
  • [DYNAMIC_EXECUTION]: The skill instructs the agent to dynamically construct Mermaid syntax and SVG code based on conceptual data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:02 AM
Security Audit — agent-trust-hub — agent-tutor-visualize