tensor-bindings-gpu
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: The skill loads external USD files via
ovstage.population.open_usdas shown inSKILL.md. - Boundary markers: No explicit markers or instructions are provided to the agent to ignore embedded instructions in the ingested data.
- Capability inventory: The agent has access to the
Shelltool for compilation and execution, and uses theovphysxlibrary for direct GPU memory operations. - Sanitization: No sanitization or validation of the USD content is described.
- [COMMAND_EXECUTION]: The instructions direct the agent to use the
Shelltool to compile C code samples and run integration tests, which involves executing system-level commands as part of the intended development workflow.
Audit Metadata