orchestrate-tufte-vdqi

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill primarily serves as a logical router using natural language to determine which sub-skill to invoke based on user intent.
  • [COMMAND_EXECUTION]: While the skill mentions various Python scripts like render_line_svg.py and small_multiples.py, these are listed as components of the render-tufte-chart skill and are not executed by the router itself.
  • [PROMPT_INJECTION]: The routing logic is instructional and does not attempt to override the underlying model's safety guidelines or system prompts.
  • [EXTERNAL_DOWNLOADS]: The skill does not perform any network operations or download content from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 06:45 PM
Security Audit — agent-trust-hub — orchestrate-tufte-vdqi