design-deliberately

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill is purely instructional and focused on design review workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill inherently processes external data provided by the user (UI components, screenshots, or code) for design auditing.
  • Ingestion points: SKILL.md (Phase 1 -- Audit) specifies reading the component or page under review.
  • Boundary markers: Absent, as the skill provides a framework for human-in-the-loop review rather than automated processing.
  • Capability inventory: No executable capabilities (subprocess calls, file-writes, or network operations) were detected in any of the skill files.
  • Sanitization: None detected, but risk is negligible as the agent only outputs text-based design prescriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 08:34 AM