ovstorage-user-getting-started

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as an onboarding and discovery tool for NVIDIA Omniverse storage (ovstorage). It uses the ovstorage_doctor tool to retrieve and display configuration metadata, such as backend types (S3, local files) and connection statuses, without performing any sensitive file operations or network exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from the ovstorage_doctor tool to inform the agent about the current environment state.
  • Ingestion points: Results returned by the ovstorage_doctor tool call in SKILL.md.
  • Boundary markers: None explicitly defined in the provided recipe.
  • Capability inventory: Read-only diagnostic discovery; the skill does not include instructions for writing data or executing arbitrary code.
  • Sanitization: Standard platform-level handling of tool output interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:49 PM
Security Audit — agent-trust-hub — ovstorage-user-getting-started