security-testing

name	security-testing
version	2.0.0
description	Comprehensive security testing automation for AI/ML systems with CI/CD integration
sasmp_version	1.3.0
bonded_agent	06-api-security-tester
bond_type	PRIMARY_BOND
input_schema	{"type":"object","required":["test_type"],"properties":{"test_type":{"type":"string","enum":["vulnerability","penetration","compliance","regression","full"]},"target":{"type":"object","properties":{"type":{"type":"string","enum":["api","model","pipeline","infrastructure"]},"endpoint":{"type":"string"}}},"config":{"type":"object","properties":{"parallel":{"type":"boolean","default":true},"timeout_seconds":{"type":"integer","default":300}}}}}
output_schema	{"type":"object","properties":{"total_tests":{"type":"integer"},"passed":{"type":"integer"},"failed":{"type":"integer"},"vulnerabilities":{"type":"array"},"coverage_percent":{"type":"number"}}}
owasp_llm_2025	["LLM01","LLM02","LLM03","LLM04","LLM05","LLM06","LLM07","LLM08","LLM09","LLM10"]
nist_ai_rmf	["Measure","Manage"]

Security Testing Automation

Automate AI security testing with comprehensive test suites, CI/CD integration, and continuous vulnerability assessment.

Quick Reference

Skill:       security-testing
Agent:       06-api-security-tester
OWASP:       Full LLM Top 10 Coverage
NIST:        Measure, Manage
Use Case:    Automated security validation

Testing Architecture

                    [Security Test Suite]
                           ↓
┌──────────────┬──────────────┬──────────────┬──────────────┐
│  Injection   │   Safety     │  Robustness  │   Privacy    │
│    Tests     │    Tests     │    Tests     │    Tests     │
└──────────────┴──────────────┴──────────────┴──────────────┘
                           ↓
                    [Result Aggregator]
                           ↓
              [Pass/Fail Gate] → [Report]

Test Framework

Core Test Suite

class AISecurityTestSuite:
    """Comprehensive AI security test framework."""

    def __init__(self, target, config):
        self.target = target
        self.config = config
        self.results = []

    def run_all_tests(self):
        """Execute complete security test suite."""
        test_categories = [
            self.test_prompt_injection,
            self.test_jailbreak_resistance,
            .test_data_leakage,
            .test_output_safety,
            .test_rate_limiting,
            .test_authentication,
        ]

         test_func  test_categories:
            :
                result = test_func()
                .results.append(result)
             Exception  e:
                .results.append(TestResult(
                    test=test_func.__name__,
                    status=,
                    error=(e)
                ))

         .aggregate_results()

     ():
        
        payloads = ._load_injection_payloads()
        vulnerable_count = 

         payload  payloads:
            response = .target.query(payload)
             ._is_injection_successful(response):
                vulnerable_count += 

        success_rate = vulnerable_count / (payloads)
         TestResult(
            test=,
            status=  success_rate >   ,
            metrics={: success_rate}
        )

     ():
        
        jailbreaks = ._load_jailbreak_suite()

        results = []
         jailbreak  jailbreaks:
            response = .target.query(jailbreak.prompt)
            success = ._detect_jailbreak_success(response, jailbreak)
            results.append({
                : jailbreak.category,
                : success
            })

        success_rate = (  r  results  r[]) / (results)
         TestResult(
            test=,
            status=  success_rate >   ,
            metrics={: success_rate}
        )

     ():
        
        probes = ._load_leakage_probes()
        leaks_found = []

         probe  probes:
            response = .target.query(probe)
             leaked := ._detect_leakage(response):
                leaks_found.append({
                    : probe,
                    : leaked.,
                    : leaked.severity
                })

         TestResult(
            test=,
            status=  leaks_found  ,
            metrics={: (leaks_found)},
            findings=leaks_found
        )