Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLIAbout this skill
Test LLM applications for prompt injection, jailbreak, data exfiltration, and indirect injection attacks — attack taxonomy, test harness design, automated red-team probes, defense patterns, and evaluation rubrics. Use when asked about "prompt injection", "jailbreak", "LLM red team", "adversarial prompts", "indirect injection", "exfiltration via LLM", "test AI security", "LLM attack surface", "OWASP LLM Top 10", "system prompt leak", "prompt leaking", or "AI safety testing". Do NOT use for: traditional app security — see red-team-check or security-review. Do NOT use for: model alignment — focus is on app layer.
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.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
2 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
- high: instruction override — SKILL.md, line 58
- high: instruction override — SKILL.md, line 88
Content SHA-256: 50a69d566498d1443675ddf55b4d43a1e3613b41990d7fb492213d1fa0a0a20c
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.