agent-safety

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as a comprehensive guide for implementing agent security guardrails, covering prompt injection defense, sandboxing, and data redaction. All recommendations align with industry best practices for secure agent design.
  • [NO_CODE]: No executable scripts or automation code are present in the provided files. The content is restricted to documentation (SKILL.md), evaluation criteria (evals/routing.yaml), and a distribution archive (agent-safety.skill).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 05:44 PM