feedback-design
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The content consists entirely of instructional design principles and does not contain any commands to override agent behavior or safety filters.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected. All links provided are for legitimate design research sources.
- [Obfuscation] (SAFE): No encoded content, zero-width characters, or homoglyphs were found in the document.
- [Unverifiable Dependencies & RCE] (SAFE): No external packages are installed and no remote scripts are executed. The provided JavaScript snippet is purely illustrative.
- [Indirect Prompt Injection] (SAFE): This skill provides static design guidelines and does not possess an attack surface for ingesting untrusted external data at runtime.
- [Metadata Poisoning] (SAFE): The metadata accurately describes the content of the skill and does not contain any malicious or deceptive instructions.
Audit Metadata