design-template-art-deco
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading a user's tech stack and writing styled components to a codebase, creating a surface for processing untrusted data.
- Ingestion points: User-provided tech stack information and design goals used to generate implementation plans.
- Boundary markers: None identified for delimiting external code content.
- Capability inventory: Accesses file-system tools including Read, Write, Edit, Glob, and Grep.
- Sanitization: Assumes standard agent guardrails; no specialized sanitization for codebase content is present within the skill.
Audit Metadata