skills/nvidia/simready-foundation/simready-foundation-conform-fet-021-robot-core/Gen Agent Trust Hub
simready-foundation-conform-fet-021-robot-core
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
uvtool to run a local validation script,validate-simready-profile. This command is executed to verify conformance after repairs are applied. The operation is restricted to the local environment and uses paths derived from provided inputs within the SimReady foundation structure. - [PROMPT_INJECTION]: The skill processes external data such as USD assets and validation reports. While this represents a surface for indirect prompt injection, the skill includes clear operational boundaries and a repair policy that limits the agent to mechanical, verifiable changes.
- Ingestion points: USD assets, validation reports, and JSON manifests (SKILL.md).
- Boundary markers: Explicit instructions and a repair policy defined in SKILL.md.
- Capability inventory: File writing (staged assets) and command execution via
uv run(SKILL.md). - Sanitization: Constraints requiring mechanical and locally verifiable repairs.
Audit Metadata