blender-content-safety-and-privacy
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for establishing a security boundary when handling untrusted 3D assets, archives, and dependencies.
- [SAFE]: The guidelines explicitly advise against the automatic execution of embedded scripts and add-ons in Blender files, mitigating risks of unauthorized code execution from untrusted content.
- [SAFE]: Instructions include protective measures for data privacy, such as excluding sensitive project details from screenshots and preventing credentials from being placed in metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface where untrusted external content could be used to influence agent behavior and provides mitigation strategies.
- Ingestion points: External .blend files, USD layers, textures, and archives as described in SKILL.md.
- Boundary markers: The skill instructs the agent to treat third-party content as untrusted and use isolated profiles.
- Capability inventory: Notes that Blender content can contain embedded scripts, drivers, and add-ons with executable capabilities.
- Sanitization: Recommends verifying file digests, inspecting metadata, and rejecting archive entries that attempt path traversal.
Audit Metadata