name: TrueFurina
title: AI Agent Security Product Manager
company: DBAPP Security
focus_areas:
- AI Agent Security Architecture & Governance
- LLM Security Risk Assessment & Red Teaming
- AI Security Product Strategy & Roadmap
- Trustworthy AI Compliance & Standards
core_competencies:
- AI Agent Security:
- Agent prompt injection defense & isolation
- RAG pipeline security & data sanitization
- Model output validation & guardrails
- Agent-to-agent communication security
- Product Management:
- End-to-end product lifecycle management
- Cross-functional team leadership
- Technical roadmap planning
- Stakeholder communication
- Security Domain:
- Threat modeling & risk assessment
- Security architecture review
- Compliance frameworks (ISO 27001, etc.)
- Security testing & validation
mission: "Building AI systems that are not only powerful, but trustworthy."
motto: "Security is not a feature — it's a foundation."Zero-touch, purely passive OSINT/EASM/CTEM platform — 15+ data sources, one command, no probes sent.
| Feature | Description |
|---|---|
| 🔍 15 Passive Data Sources | crt.sh, HackerTarget, OTX, URLScan, Wayback, DNSDumpster, CommonCrawl, GitHub, Hunter, FOFA, SecurityTrails, Shodan, VirusTotal, ZoomEye, Qichacha |
| 🚀 One Command | |
| 🛡️ Compliance Guardrail | Fail-closed R1 compliance on every outbound call |
| 🌐 Web Dashboard | — one-click panel |
| ⏰ Auto Scheduler | Daily collection with change tracking |
Goal: 1000 Stars ⭐
⭐ Star on GitHub · 📖 README · 🌐 Website
DBAPP Security | 2023 - Present
Leading the development of AI Agent security products from concept to delivery. Focused on securing enterprise AI Agent deployments across multiple industries.
Product Strategy & Roadmap
- Defined and executed product roadmap for AI Agent security product line, covering LLM security assessment, Agent behavior monitoring, and security governance
- Conducted competitive analysis and market research to identify gaps in AI security product landscape
- Established product vision and OKRs aligned with company's AI security strategy
Product Development & Delivery
- Led cross-functional teams (engineering, research, design) to deliver AI security products on schedule
- Defined product requirements and technical specifications for Agent security features
- Managed product backlog, prioritized features based on risk impact and customer needs
- Drove go-to-market strategy and customer onboarding
Security Research & Standards
- Developed internal frameworks for LLM vulnerability assessment and red teaming
- Contributed to AI security standards and best practices documentation
- Built security evaluation benchmarks for Agent behavior analysis
- Led the launch of AI Agent security assessment product, serving enterprise customers
- Built security evaluation framework covering 50+ attack vectors for LLM-based Agents
- Established internal AI security red teaming process from ground up
| Competency | Proficiency | Details |
|---|---|---|
| LLM Security Assessment | ⚡ Advanced | Prompt injection, jailbreaking, data leakage, model extraction |
| Agent Security Architecture | ⚡ Advanced | Isolation, sandboxing, privilege control, inter-agent security |
| RAG Security | ⚡ Advanced | Document sanitization, context isolation, retrieval poisoning defense |
| Security Governance | ⚡ Advanced | Policy definition, compliance monitoring, audit trails |
| Red Teaming | 🔷 Expert | Attack simulation, vulnerability discovery, remediation guidance |
| Competency | Proficiency | Details |
|---|---|---|
| Product Strategy | ⚡ Advanced | Roadmap planning, market analysis, competitive intelligence |
| Requirements Management | ⚡ Advanced | PRD writing, user story mapping, prioritization frameworks |
| Cross-functional Leadership | ⚡ Advanced | Engineering, research, design, marketing coordination |
| Data-Driven Decision Making | ⚡ Advanced | Metrics definition, A/B testing, user research |
| Skill | Proficiency | Details |
|---|---|---|
| Python | ⚡ Advanced | Security tooling, data analysis, automation |
| AI/ML Fundamentals | ⚡ Advanced | LLM architecture, RAG, fine-tuning, embeddings |
| Security Tools | 🔷 Expert | Burp Suite, OWASP methodologies, threat modeling |
| Data Analysis | ⚡ Advanced | SQL, statistics, visualization, analytics |
Role: Product Manager (Lead) Status: Launched, serving enterprise customers
An enterprise-grade security assessment platform for AI Agent systems. Covers the full lifecycle of Agent security evaluation — from architecture review to runtime monitoring.
Key features:
- Multi-dimensional LLM security testing (50+ attack vectors)
- Agent behavior analysis and anomaly detection
- Automated compliance reporting
- Real-time security monitoring dashboard
Impact:
- Reduced enterprise Agent security assessment time by 60%
- Identified and helped remediate 200+ security vulnerabilities pre-launch
- Established industry benchmark for Agent security evaluation
Role: Technical Product Manager Status: Internal tool, deployed across teams
A systematic framework for red teaming LLM-based applications. Designed to be extensible, repeatable, and actionable.
Key features:
- Automated attack scenario generation
- Multi-turn conversation attack simulation
- Vulnerability classification and severity scoring
- Remediation recommendation engine
Impact:
- Standardized security testing process across 5+ product teams
- Discovered 30+ novel attack patterns in production Agents
- Reduced security review cycle from weeks to days
Role: Product Strategy Lead Status: Research & Standards
A comprehensive governance framework for enterprise AI deployment, covering security, privacy, compliance, and ethics.
Key components:
- AI risk classification and assessment methodology
- Security control requirements by risk level
- Compliance mapping (ISO 27001, GDPR, etc.)
- Continuous monitoring and improvement process
| Certification | Area |
|---|---|
| AI Security & Governance | Internal Enterprise AI Security Framework |
| Product Management | End-to-end Product Lifecycle |
| Security Assessment | OWASP / Threat Modeling |
| Data Protection | ISO 27001 Compliance |