human-taste
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious instructions, prompt injections, or obfuscated code were identified within the skill's markdown or reference files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to evaluate untrusted external data such as screenshots, wireframes, and UI descriptions. While this provides an attack surface for indirect prompt injection, the risk is mitigated because the skill does not utilize any dangerous capabilities like network access, file system modification, or command execution.
- [EXTERNAL_DOWNLOADS]: The skill contains informational references to well-known academic and industry sources such as Nature, arXiv, and Paul Graham's essays. These are documented neutrally as research sources and do not include executable scripts or untrusted dependencies.
Audit Metadata