frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The skill uses instructional markers like 'CRITICAL' and 'IMPORTANT', but these are used to emphasize design quality and aesthetic choices rather than bypassing safety filters or overriding core agent instructions.
- Data Exposure & Exfiltration (SAFE): No network operations, hardcoded credentials, or sensitive file access patterns were detected in the skill definition.
- Obfuscation (SAFE): No hidden characters, encoded strings (such as Base64), or homoglyphs were found in the text.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not perform package installations or execute remote scripts. It suggests using libraries like 'Motion' in the generated output, which is standard for frontend development tasks.
- Indirect Prompt Injection (LOW):
- Ingestion points: The skill processes user-provided frontend requirements (SKILL.md).
- Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the user's requirements.
- Capability inventory: The skill directs the agent to generate functional code (HTML/CSS/JS/React/Vue) which is a standard capability for this use case.
- Sanitization: None observed.
- Dynamic Execution (SAFE): While the purpose of the skill is to generate code, it does not contain mechanisms to execute that code within the skill's own context or via unsafe functions like eval().
Audit Metadata