styleseed-design-review
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a collection of natural language instructions and design heuristics. It does not contain any scripts, binary files, or shell commands.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted UI code provided by users. While this presents an attack surface where malicious instructions could be embedded in code comments to influence the agent's review (e.g., forcing a high score), the risk is minimal as the skill has no capabilities for network exfiltration, file modification, or command execution.
- Ingestion points: Local UI code files (React, Tailwind, HTML) provided as input.
- Boundary markers: None; the agent is instructed to use evidence-based scoring to mitigate hallucination or manipulation.
- Capability inventory: No file system writes, network requests, or subprocess executions are defined.
- Sanitization: The skill relies on the agent's internal instruction-following logic to differentiate between UI code and instructional prompts.
Audit Metadata