interface-design
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses behavioral steering to encourage the agent to produce high-quality, non-generic design outputs. These are instructional and do not attempt to bypass safety filters.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting user-provided design requirements and persisting generated patterns to a local file.
- Ingestion points: User-provided interface descriptions and project-specific ".interface-design/system.md" configuration.
- Boundary markers: Uses internal state checkpoints (Intent, Palette, Depth, etc.) to structure thoughts, but does not provide explicit isolation for external content.
- Capability inventory: File system write access to ".interface-design/system.md" for pattern persistence.
- Sanitization: None detected for user-supplied design context before it is processed or stored.
- [SAFE]: No evidence of credential harvesting, unauthorized network connections, or malicious persistence mechanisms was found.
Audit Metadata