ovphysx-drop-contact-acceptance
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing a local Python script
scripts/run_ovphysx_drop_probe.pywith the--require-realargument. This script is used to interface with the installed OVPhysX runtime to perform authoritative pose readback and simulation validation. - [INDIRECT_PROMPT_INJECTION]: The skill processes complex external data formats which represent a surface for indirect instructions, although this is inherent to the simulation task.
- Ingestion points: The agent is instructed to read and work from user-provided
.blend(Blender) andUSD(Universal Scene Description) files. - Boundary markers: None are explicitly defined to delimit data from instructions within these binary/scene formats.
- Capability inventory: The skill has the capability to execute shell commands (
python3) and perform file system operations (read source files, write artifacts to a working directory). - Sanitization: There are no mentioned sanitization or validation steps for the content of the ingested scene files beyond verifying transforms and non-overlap for physics stability.
Audit Metadata