simready-foundation-conform-fet-021-robot-core

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the uv tool to execute a local validation command validate-simready-profile. This is the primary mechanism for verifying that the robot assets meet the FET021 specification requirements.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted input data, including USD assets and validation reports.
  • Ingestion points: Data enters the context through usd_asset and validation_report files (referenced in SKILL.md).
  • Boundary markers: No explicit XML or triple-backtick delimiters are defined for the untrusted data ingestion.
  • Capability inventory: Subprocess execution via uv run (SKILL.md) and file system write operations (SKILL.md).
  • Sanitization: The skill mitigates risk by requiring the agent to work on staged copies of assets rather than mutating source files directly, and mandates manual inspection of the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 11:05 AM
Security Audit — agent-trust-hub — simready-foundation-conform-fet-021-robot-core