simready-prop-journey
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external source files (Blender props) provided by the user, which serves as an ingestion point for potentially untrusted data. The skill mitigates this risk by explicitly instructing the agent to use a safety-focused sub-skill,
blender-content-safety-and-privacy, when dealing with untrusted inputs. - Evidence:
- Ingestion point: Step 1 involves preserving and working on a supplied source.
- Capability: Step 4 executes a native behavior check via a Python script.
- Sanitization: Instructions mandate using a content safety skill for untrusted inputs.
- [COMMAND_EXECUTION]: The workflow requires executing a specific Python script,
run_ovphysx_drop_probe.py, to perform physics validation. This script is identified as an official vendor tool for behavior checks. - Evidence:
- SKILL.md: Step 4 references the execution of
run_ovphysx_drop_probe.py --require-real.
Audit Metadata