frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by taking user-provided requirements and generating production-grade frontend code (HTML, CSS, JS, React, Vue). This design creates an attack surface where a user could provide instructions containing embedded malicious prompts intended to manipulate the generated code output.
- Ingestion points: User frontend requirements (as described in SKILL.md).
- Boundary markers: Absent; the skill does not specify delimiters or instructions for the agent to ignore commands within the user input.
- Capability inventory: The skill is designed to produce functional code based on input but does not invoke external system tools or network capabilities within its own instructions.
- Sanitization: Absent; no validation, escaping, or filtering of the user-provided context is described in the guidelines.
Audit Metadata