simready-foundation-add-feature-adapter
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructions and metadata for the SimReady framework. It does not include executable scripts, external downloads, or network operations. Analysis of the instructions confirms they are aligned with legitimate development practices for NVIDIA's USD-based asset pipeline.
- [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection as it instructs the agent to ingest and process external data. 1. Ingestion points: feature manifests, profile versions, and test assets (SKILL.md). 2. Boundary markers: absent. 3. Capability inventory: the skill allows the agent to create Python adapter files and mutate USD stages (SKILL.md). 4. Sanitization: no explicit validation or escaping is defined for the ingested data. This is assessed as a low-risk surface common to development tools.
Audit Metadata