skills/nvidia/simready-foundation/simready-foundation-validate-foundation-change/Gen Agent Trust Hub
simready-foundation-validate-foundation-change
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 untrusted input in the form of repository diffs and manifests to perform consistency audits.
- Ingestion points: User-provided file lists and contents via
changed_filesandtarget_feature_profilein SKILL.md. - Boundary markers: Absent; the instructions do not define specific delimiters for separating user-provided data from agent instructions.
- Capability inventory: The agent is instructed to run local tools such as
simready-validate, USD/PXR, and Python syntax checkers. - Sanitization: Absent; the skill does not explicitly describe filtering or sanitizing the input data before processing.
- [COMMAND_EXECUTION]: The instructions direct the agent to execute local validation commands including
simready-validate, USD/PXR, and Python syntax/import checks. These are standard operations for the skill's auditing and validation purpose.
Audit Metadata