26zl AI Threat Testing
Test LLM applications for OWASP LLM Top 10 vulnerabilities using 10 specialized agents. Use for authorized AI security assessments.
Quick Start
1. Specify target (LLM app URL, API endpoint, or local model)
2. Select scope: Full OWASP Top 10 | Specific vulnerability | Supply chain
3. Agents deploy, test, capture evidence
4. Professional report with PoCs generated
Primary Agents
Each agent targets one OWASP LLM vulnerability:
- Prompt Injection (LLM01): Direct/indirect injection, system prompt extraction
- Output Handling (LLM02): Code/XSS injection, unsafe deserialization
- Training Poisoning (LLM03): Membership inference, backdoors, data extraction
- Resource Exhaustion (LLM04): Token flooding, DoS, cost impact
- Supply Chain (LLM05): Dependency scanning, plugin security
- Excessive Agency (LLM06): Privilege escalation, unauthorized actions
- Model Extraction (LLM07): Query-based theft, data reconstruction
- Vector Poisoning (LLM08): RAG injection, retrieval manipulation
- Overreliance (LLM09): Hallucination testing, confidence manipulation
- Logging Bypass (LLM10): Monitoring evasion, forensic gaps
See reference/llm0X-*.md for attack playbooks.
Workflows
Full Assessment (4-8 hours):
- [ ] Reconnaissance
- [ ] Deploy all 10 agents
- [ ] Execute exploits
- [ ] Capture evidence
- [ ] Generate report
Focused Testing (1-3 hours):
- [ ] Select vulnerability (LLM01-10)
- [ ] Deploy agent
- [ ] Execute techniques
- [ ] Document findings
Supply Chain Audit (2-4 hours):
- [ ] Inventory dependencies
- [ ] Scan CVEs
- [ ] Test plugins/APIs
- [ ] Verify model provenance
Integration
Enhances /pentest with AI-specific testing:
- Traditional pentesting + AI threat testing = complete security assessment
- Chain vulnerabilities across traditional and AI vectors
- Unified reporting with CVSS scores
Key Techniques
Prompt Injection: Instruction override, system prompt extraction, filter evasion
Model Extraction: Query sampling, token analysis, membership inference
Data Poisoning: Behavioral anomalies, backdoor triggers, bias analysis
DoS: Token flooding, recursive expansion, context exhaustion
Supply Chain: CVE scanning, plugin audit, model verification
MCP Tool Abuse: MCP server inspectors/debuggers often expose /api/mcp/connect or similar endpoints that accept serverConfig with arbitrary command parameters — unauthenticated RCE. Check for MCP Inspector, MCP Playground, or any MCP debugging UI on non-standard ports (6274, 3000, etc.).
Evidence Capture
All agents collect: screenshots, network logs, API responses, errors, console output, execution metrics.
Reporting
Automated reports include: executive summary, detailed findings (CVSS scores), PoC scripts, evidence, remediation guidance.
Critical Rules
- Written authorization REQUIRED before testing
- Never exceed defined scope
- Test in isolated environments when possible
- Document all findings with reproducible PoCs
- Follow responsible disclosure practices
Integration
- Integrates with
/pentestskill for comprehensive security testing - AI-specific vulnerability knowledge in
/AGENTS.md - Attack playbooks in
reference/llm0X-*.md