stitch-design-taste
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and templates for generating design documentation. It does not include any scripts, executable binaries, or system-level commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to transform user-provided project descriptions into structured design rules. While it lacks explicit output sanitization or boundary markers, the risk is negligible as the skill lacks capabilities beyond text output. 1. Ingestion points: User descriptions of project intent and atmosphere. 2. Boundary markers: Absent in the generated DESIGN.md template. 3. Capability inventory: No tools or dangerous capabilities are invoked. 4. Sanitization: None identified beyond standard LLM guardrails.
- [SAFE]: No obfuscated content, hardcoded credentials, or persistence mechanisms were detected in the skill's instructions or metadata.
Audit Metadata