simready-foundation-conform-fet-000-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 processes external data including USD assets and validation reports, establishing an attack surface for indirect prompt injection.
- Ingestion points: Input files such as
usd_asset,validation_report, andmujoco_overridesare read into the agent context. - Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore embedded commands in the source data.
- Capability inventory: The agent performs file system modifications on USD assets and executes local shell commands for validation.
- Sanitization: There is no evidence of sanitization or content validation for the external input data before it is processed.
- [COMMAND_EXECUTION]: The validation procedures involve executing shell commands to configure the environment and verify the repairs.
- Commands utilizing
repo.batanduvare used to build project components and manage dependencies. - The agent is instructed to install and use packages like
usd-coreandusd-validation-nvidia, which are appropriate for the vendor-specific tasks defined in the skill.
Audit Metadata