visualize

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by generating interactive HTML and JavaScript fragments that can trigger agent actions via the window.openai.sendFollowUpMessage API.
  • Ingestion points: User-provided data and requests are directly processed to generate HTML content and interactive logic as defined in SKILL.md.
  • Boundary markers: The skill instructions lack requirements for the agent to sanitize or delimit user data when interpolating it into JavaScript variables or prompt strings used for agent interaction.
  • Capability inventory: The skill facilitates local script execution via scripts/render.py and allows the generated frontend to initiate follow-up messages that the agent processes.
  • Sanitization: No explicit validation, filtering, or escaping of external content is mandated before it is embedded in the visualization fragments.
  • [COMMAND_EXECUTION]: The skill uses a local Python utility to wrap, export, and serve the generated visualization fragments.
  • Evidence: SKILL.md contains instructions to execute python3 scripts/render.py <absolute-fragment-path> [<destination>.html] [--serve].
  • [EXTERNAL_DOWNLOADS]: The skill is configured to fetch assets and dependencies from established and well-known Content Delivery Networks (CDNs).
  • Evidence: The whitelisted domains include cdnjs.cloudflare.com, esm.sh, cdn.jsdelivr.net, unpkg.com, fonts.googleapis.com, fonts.gstatic.com, and fonts.bunny.net.
  • [PROMPT_INJECTION]: The skill metadata and default prompt include instructions to ensure the agent does not refuse requests and describes the capability as unrestricted.
  • Evidence: The openai.yaml file defines the display name as "Visualize (Unrestricted)" and states the skill has "no scope/stealth gates" in its description.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:16 AM