Oathe Security Badge

Is jzOcb/agent-guardrails safe?

https://github.com/jzOcb/agent-guardrails

95
SAFE

This is a legitimate development tools skill that provides mechanical enforcement capabilities for AI agent projects through git hooks, secret detection, and deployment verification scripts. The skill performs as advertised with no evidence of malicious behavior, data exfiltration, or prompt injection.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 100/100 · 25%
Code Execution 85/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 90/100 · 5%

Findings (2)

LOW Installs executable scripts and git hooks -15

The skill installs shell scripts and git pre-commit hooks as part of its intended functionality for enforcing coding standards. While legitimate for this purpose, executable code installation always carries inherent risk.

INFO Development tools with legitimate enforcement capabilities -10

This skill provides legitimate mechanical enforcement tools for AI agent projects including git hooks, secret detection, and deployment verification. The functionality matches the stated purpose.