Back to directory

Scan LLM Systems for Jailbreaks Prompt Injections and Unsafe Beh

Agent skill

AGENT SKILLS ATLAS

Scan LLM Systems for Jailbreaks Prompt Injections and Unsafe Beh

Probe a model or agent stack with adversarial test suites so safety failures show up before deployment or review.

Install with

Claude Code

Codex

Cursor

GitHub Copilot

Gemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryEngineeringStars0

About this skill

Probe a model or agent stack with adversarial test suites so safety failures show up before deployment or review.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Unavailable

Unsupported source URL

About scan coverage and limitations

Original listing metadata

Original name

scan-llm-systems-for-jailbreaks-prompt-injections-and-unsafe-beh

Original description

Probe a model or agent stack with adversarial test suites so safety failures show up before deployment or review.

About this listing

Category: Engineering
Reported license: Not specified
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.

Scan LLM Systems for Jailbreaks Prompt Injections and Unsafe Beh | Agent Skills Atlas