design-an-interface

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and associated files do not contain any malicious code, external downloads, or unauthorized command execution patterns.
  • [PROMPT_INJECTION]: The skill demonstrates a standard indirect prompt injection surface by interpolating user-provided module descriptions into prompts for sub-agents. Ingestion points: User requirements are interpolated into variables in the SKILL.md template. Boundary markers: Absent. Capability inventory: Uses the Task tool to spawn sub-agents for parallel processing. Sanitization: None. This surface is expected behavior for a tool designed to process and reason about user-provided technical specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 04:29 AM
Security Audit — agent-trust-hub — design-an-interface