webgl-experience

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text from the 'subject' field to generate WebGL code. This creates an attack surface where malicious instructions within the user input could potentially influence the agent's code generation logic.\n
  • Ingestion points: User input is ingested via the subject parameter defined in open-design.json.\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate user-provided data from agent instructions during interpolation.\n
  • Capability inventory: The skill utilizes the fs:write capability (as noted in open-design.json) to output the resulting HTML and shader code to the file system.\n
  • Sanitization: There are no defined procedures for validating, filtering, or escaping the user-provided input before it is used to drive code generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:20 AM
Security Audit — agent-trust-hub — webgl-experience