spawning-reviewers

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill provides instructions and prompt templates for optimizing agent-based reviews using model diversity and adversarial techniques.
  • [SAFE]: The skill includes explicit instructions to mitigate indirect prompt injection (Category 8) by advising reviewer agents to ignore comments and self-descriptions within analyzed artifacts and instead re-derive understanding from the raw source material.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 12:30 PM
Security Audit — agent-trust-hub — spawning-reviewers