stitch-design-taste
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of Markdown instructions and design templates. No executable code, scripts, binary files, or remote dependencies are included in the package.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions of project intent or aesthetic "vibe" to generate a DESIGN.md file. This content is intended for consumption by a downstream AI agent (Google Stitch).
- Ingestion points: User-supplied project descriptions and vibe adjectives defined in SKILL.md.
- Boundary markers: No specific delimiters or safety instructions are used to wrap the user-provided input.
- Capability inventory: The skill has no active capabilities; it does not perform subprocess calls, file system writes, or network requests.
- Sanitization: No sanitization or filtering is applied to the user input before it is used to generate the design documentation.
Audit Metadata