alterlab-vcd-exhibition
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized data access patterns were identified. The skill follows standard professional workflows for environmental design.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present but considered safe within the intended use case. 1. Ingestion points: The skill reads user-provided project files (floor plans, briefs) and searches the web for design trends. 2. Boundary markers: None are present in the provided templates to isolate external data. 3. Capability inventory: The agent can search the web and write markdown documentation to the project directory. 4. Sanitization: No explicit sanitization of external input is defined. This surface is consistent with the primary purpose of the skill.
Audit Metadata