neobrutalist-web-designer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- Prompt Injection (SAFE): No instructions found that attempt to override agent behavior, bypass safety filters, or reveal system prompts.
- Data Exposure & Exfiltration (SAFE): The skill contains no logic for accessing local files or sending data to external servers. All URLs provided are static references to legitimate design resources.
- Remote Code Execution (SAFE): No package manager files (package.json, requirements.txt), script files, or remote execution patterns (curl|bash) are present.
- Indirect Prompt Injection (SAFE): The skill consists of markdown-based reference material. It lacks any capability to ingest or process untrusted external data at runtime, eliminating the risk of indirect injection.
- Obfuscation (SAFE): No encoded strings, homoglyphs, or hidden characters were detected in the provided markdown files.
Audit Metadata