product-grid-scene-planner
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of instructional documentation and planning schemas. It does not include any scripts, executable commands, or external network requests. All referenced files and hand-offs are internal to the skill directory.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product lists and briefs but lacks any capability to execute code or perform network operations, mitigating potential injection risks. 1. Ingestion points: locked_3d_brief and product_variant_inventory in contract.json. 2. Boundary markers: None present. 3. Capability inventory: None (L0 capability tier). 4. Sanitization: None present.
Audit Metadata