run-operations
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs and executes shell commands to run the
usdOptimizebinary located in the project's_builddirectory. It usesBashto invoke the tool with various arguments provided by the user. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests untrusted data from external USD files (
.usd,.usda,.usdc,.usdz) as defined in theStep 1andStep 3sections ofSKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded content within the USD files are mentioned.
- Capability inventory: The skill has the capability to execute shell commands, write to the filesystem (output stages and logs), and run processes in the background.
- Sanitization: The skill does not describe any specific sanitization or validation of the internal content of the USD files beyond path existence checks.
Audit Metadata