webgl-particle-galaxy

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill and its associated files (SKILL.md, example.html, open-design.json) contain standard development practices for WebGL2 visualizations. The code is self-contained and does not perform any external network requests or sensitive file access.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design, as it ingests data from external sources to influence code generation.
  • Ingestion points: The skill instructions (Step 3) specify that accent colors should be mapped from an active DESIGN.md file if present.
  • Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore potentially malicious instructions embedded within the DESIGN.md file.
  • Capability inventory: The skill uses fs:write to generate the final index.html file based on these inputs.
  • Sanitization: There are no documented sanitization or validation steps for the data interpolated from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:20 AM
Security Audit — agent-trust-hub — webgl-particle-galaxy