simready-foundation-conform-fet-004-mujoco
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from external, potentially untrusted sources including validation reports, profile TOML files, and user requests.\n
- Ingestion points: Workflow Step 1 in SKILL.md identifies validation reports and profile TOMLs as input.\n
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided in the instructions.\n
- Capability inventory: The skill allows for modifying USD files and executing the workspace upgrade command.\n
- Sanitization: No sanitization or validation logic for the ingested reports is described.\n- [COMMAND_EXECUTION]: The skill references the execution of the workspace upgrade command as part of the feature adapter workflow, which is an internal NVIDIA tool for asset management.
Audit Metadata