skills.rest
pluginagentmarketplace
pluginagentmarketplaceCOMMUNITY
Explore all skills by this author →
GitHub

security-testing

Automate AI security testing for models, APIs, and pipelines in CI/CD workflows.

3|Updated Nov 18, 2025
Search Tags:#vulnerability#CI/CD#security testing#AI#jailbreak#data leakage#prompt-injection
One-click install
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill security-testing-pluginagentmarketplace
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-testing
Source: https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming/tree/main/skills/security-testing
Command: npx skills add https://github.com/pluginagentmarketplace/custom-plugin-ai-red-teaming --skill security-testing-pluginagentmarketplace

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides automated, end-to-end security testing for AI/ML workflows, integrating robust checks into CI/CD to continuously validate models, data handling, and responses.

Core Features & Use Cases

  • Automated security checks across prompts, jailbreak resistance, data leakage detection, and output safety.
  • CI/CD integration to run security tests on every push or PR, with configurable thresholds and reporting.
  • Use Case: Integrate into your ML lifecycle to catch prompt-injection and data exposure before deployment.

Quick Start

Install and enable the security-testing Skill in your Claude Code environment and provide an input according to the defined schema to trigger automated tests. For example, configure a test_type and target in your deployment pipeline and observe test results via the assets/test-suite.yaml configuration and the scripts/run-tests.py runner.

Frequently Asked Questions about security-testing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI security testing in a CI/CD pipeline?▼

You can automate AI security testing by configuring a YAML-based test suite and a Python runner to validate prompts, prevent data leakage, and enforce safety constraints within your CI/CD workflow on every push or PR.

What is prompt-injection and how do I test for jailbreaks in AI models?▼

Prompt-injection and jailbreaks manipulate AI model behavior to bypass safety rules. You test for them by running automated security checks that validate prompt robustness and detect jailbreak resistance before model deployment.

Does the security-testing Skill support parallel execution and structured input?▼

Yes, the Skill satisfies a structured input/output schema and supports parallel execution to efficiently run multiple security tests across your AI/ML deployments, models, and APIs.

Can I use YAML to configure data leakage detection for AI/ML deployments?▼

Yes, you can configure a YAML-based test suite to define and execute data leakage detection and output safety checks for your AI/ML deployments across models and APIs.

Do I need pyyaml to run automated security tests for AI models?▼

Yes, the pyyaml dependency is required to parse the YAML-based test suite configuration and execute the Python runner for automated AI security testing across your pipelines.

What are the limitations of using YAML test suites for prompt-injection testing?▼

YAML test suites for prompt-injection testing rely on predefined scenarios and configurable thresholds, meaning they may not catch novel or zero-day jailbreak techniques without continuous test suite updates.

Related Skills

Explore More Software Engineering Skills→
agentclashagentclash
25

agentclash-challenge-pack-input-sets

Create standardized, YAML-based input sets for AgentClash challenge packs with schema validation.

Official
Intermediate
HelloEverybobyHelloEveryboby
17

LLMSecurityTester

Test AI models for prompt injection and jailbreak vulnerabilities.

Community
Advanced
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
ContextJet-aiContextJet-ai
29

red-team-llm-app

Red-team LLM applications against security vulnerabilities like prompt injection and jailbreaks.

Official
Advanced