vois-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a comprehensive design system guide for AI agents, establishing architectural rules for UI layout before implementation. It does not contain executable code, installation scripts, or remote execution triggers.
- [SAFE]: Telemetry features are transparently documented. The skill utilizes environment-specific tools (e.g.,
vois_record_pattern_choice) and references PostHog, a well-known analytics service, for pattern usage analysis. This is part of its documented agentic feedback loop. - [SAFE]: All external references, such as links to Mobbin, are directed toward well-known design inspiration platforms. No suspicious or obfuscated URLs were found.
- [SAFE]: The skill actively promotes security best practices, such as instructing the agent to keep personally identifiable information (PII) out of URLs and analytics, and to mask sensitive data by default (PII-MASK and PII-KEEP-OUT rules).
- [SAFE]: There are no indicators of prompt injection, privilege escalation, or persistence mechanisms. The YAML frontmatter and file structure are consistent with the stated purpose.
Audit Metadata