anti-ui-slop
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, executable scripts, or hidden commands were detected. The skill is comprised of markdown documentation and configuration metadata intended for design guidance.
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and process external data, specifically local project files like product briefs and design systems, which represents a standard ingestion surface.
- Ingestion points: Identified in
SKILL.mdand thereference/playbooks, where the agent is told to read the brief and existing components. - Boundary markers: The skill explicitly instructs the agent that local project constraints and design systems "always outrank this skill."
- Capability inventory: No dangerous capabilities such as file-writing, shell command execution, or network exfiltration are present in the skill's own files.
- Sanitization: The skill relies on natural language instructions to limit the scope of information processed to design-relevant metadata.
Audit Metadata