threejs-aaa-graphics-builder
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze external data such as screenshots and renderer logs to evaluate visual quality (SKILL.md, references/visual-scorecard.md). This creates a surface for indirect prompt injection if the ingested data contains malicious instructions.
- Ingestion points: Screenshots and diagnostic logs (SKILL.md).
- Boundary markers: None.
- Capability inventory: None.
- Sanitization: Not specified.
Audit Metadata