asset-discovery
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates in a text-only, planning-only mode. It explicitly excludes downloading, fetching, or installing assets, and does not interact with the network or run Blender. It adheres to strict internal laws regarding runtime boundaries and evidence requirements.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting external data (an 8-slot brief from an upstream skill). However, because the skill lacks any high-privilege capabilities such as shell execution, file system modification, or network requests, there is no viable path for an injection to cause harm.
- Ingestion points: Reads a structured 3D brief from
intent-to-3d-brief-writer(SKILL.md). - Boundary markers: None explicitly defined for the input data.
- Capability inventory: No subprocess calls, file-write operations, or network requests are present in the skill.
- Sanitization: No specific sanitization logic is implemented for the incoming brief data.
Audit Metadata