claude-design-brief
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate design tool intended to streamline the creation of UI mockups. It provides comprehensive guidelines for typography, color palettes, and layout variations without using any dangerous command patterns or unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions. Ingestion points: Reads source material including research docs, brand briefs, site URLs, and brainstorm transcripts (SKILL.md, Step 1). Boundary markers: None identified; the skill summarizes or quotes rules into the generated prompt without specific delimiters. Capability inventory: Uses Read, Write, Edit, Glob, Grep, and Bash tools (SKILL.md frontmatter). Sanitization: None identified; external content is summarized or quoted directly into the output prompt.
Audit Metadata