design-agent-briefing

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and configuration metadata. It does not contain any executable scripts, shell commands, or network operations.
  • [SAFE]: No prompt injection, data exfiltration, or obfuscation patterns were detected within the instructions or configuration files.
  • [SAFE]: The skill uses the disable-model-invocation: true flag in its frontmatter, which restricts the agent's ability to invoke external tools, providing an additional layer of safety.
  • [SAFE]: All instructions are focused on helping the user clarify design problems and generating text-based prompts for other design agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 10:36 AM
Security Audit — agent-trust-hub — design-agent-briefing