frontend-development
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill promotes industry-standard security practices, including typed environment variable management and human-in-the-loop validation.
- [NO_CODE]: The skill package consists exclusively of markdown documentation. It does not include any executable scripts, binaries, or automated installation logic.
- [INDIRECT_PROMPT_INJECTION]: The skill's core function is to process external design specifications, which constitutes a theoretical attack surface for indirect instructions.
- Ingestion points: Design artifacts such as Figma handoff packages and screen specifications are processed as primary inputs.
- Boundary markers: The 'Accept Handoff' section requires the agent to restate design intent and verify design tokens before proceeding.
- Capability inventory: The agent performs file generation for project architecture, UI components, and API clients.
- Sanitization: The 'Gate 5 Human Approval' provides a manual checkpoint for all implemented code before it is integrated.
Audit Metadata