Skills
Navigate
skills/nvidia/simready-foundation/simready-foundation-conform-fet-001-standard/Gen Agent Trust Hub

simready-foundation-conform-fet-001-standard

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 external data (USD assets and validation reports) and performs file operations and shell command execution based on that data.
  • Ingestion points: The skill ingests usd_asset and validation_report (JSON or Markdown) as primary inputs in SKILL.md.
  • Boundary markers: The instructions do not specify any boundary markers or instructions to isolate the agent from potential malicious instructions embedded in the external asset files or reports.
  • Capability inventory: The skill allows for file system writes (to repair USD assets) and shell command execution using the uv run utility in SKILL.md.
  • Sanitization: No sanitization or validation of the content within the input assets or reports is performed before the agent processes and acts upon them.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using uv run in SKILL.md to perform asset validation. These commands, such as validate-usd-minimum and validate-simready-profile, take variables derived from inputs like <staged-usd> and <profile>.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 05:22 PM
Security Audit — agent-trust-hub — simready-foundation-conform-fet-001-standard