frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied design briefs to generate frontend code, which is a standard surface for indirect prompt injection.
- Ingestion points: User-provided design briefs described in the design process (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters for separating user-provided content from agent instructions.
- Capability inventory: Generation of HTML, CSS, and layout wireframes.
- Sanitization: Absent; no validation or filtering of the brief content is defined.
- [SAFE]: The skill is pinned from a trusted organization's repository and uses a standard Apache 2.0 license. No malicious patterns, obfuscation, or unauthorized network operations were detected.
Audit Metadata