threejs-debug-profiler
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown-based checklists and guidelines for Three.js development. No executable scripts, dangerous commands, or unauthorized network operations were identified across any of the included files.- [PROMPT_INJECTION]: The skill uses instructional language to enforce a specific debugging methodology (e.g., 'Non-negotiables'). These instructions are confined to the intended operational scope of the skill and do not attempt to bypass safety filters or manipulate the underlying agent behavior.- [INDIRECT_PROMPT_INJECTION]: The workflow involves analyzing untrusted data such as browser console errors and network logs. While this creates a potential ingestion point for malicious instructions, the skill does not automate the execution of such content and focuses on manual diagnostic metrics. (Ingestion points: SKILL.md, scene-debugging.md; Capability inventory: No automated execution or file-write tools; Sanitization: Not applicable; Boundary markers: Absent).
Audit Metadata