
Sign up to save your podcasts
Or


Summary
This episode explores the top 10 security risks associated with deploying large language models (LLMs) and AI systems. It provides practical insights and mitigation strategies to help organizations secure their AI implementations effectively.
Keywords
AI security, LLM risks, prompt injection, data leakage, supply chain security, poisoning, output handling, system prompt leakage, misinformation, resource exhaustion
Key topics
Prompt injection vulnerabilities
Sensitive data leakage in AI systems
Supply chain risks in AI deployment
Data and model poisoning techniques
Handling AI-generated outputs securely
Managing AI agent autonomy and permissions
System prompt leakage and its implications
Weaknesses in vector and embedding systems
Hallucinations and misinformation in AI
Resource exhaustion and denial of service in AI
Chapters
00:00 Introduction to AI Security Risks
04:55 Prompt Injection: The King of Vulnerabilities
11:48 Supply Chain Vulnerabilities in AI Systems
18:47 Improper Output Handling and Its Risks
24:59 Misinformation and Hallucination Problems
Resources
OWASP Top 10 for Large Language Models (https://owasp.org/www-project-top-10-for-large-language-model-applications/)
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the security risks associated with AI agents, focusing on the OWASP top 10 vulnerabilities and practical mitigation strategies. Learn how autonomous systems can be secured to prevent catastrophic failures and protect organizational assets.
Key topics
AI agent security risks
OWASP top 10 for agent applications
Mitigation strategies for autonomous systems
Chapters
00:00 The Nine-Second Database Incident
01:42 The Growing Threat of Autonomous System Incidents
02:19 Defining AI Agents and Their Architecture
03:14 Understanding Policies and Human in the Loop (HITL)
05:50 Agent Goal Hijacking and Prompt Injection
07:14 Tool Misuse, Poisoning, and Exploitation
08:53 Identity and Privilege Abuse in AI Agents
09:48 Supply Chain Vulnerabilities in AI Systems
11:40 Unexpected Code Execution Risks
12:55 Memory and Context Poisoning
14:16 Insecure Interagent Communication
15:53 Cascading Failures and Uncontrolled Amplification
17:22 Human Trust Exploitation and Social Engineering
19:01 Rogue Agents and Goal Misalignment
20:35 Five Themes for Securing AI Agents
22:46 Starting Your AI Security Inventory
Resources
OWASP Top 10 for Agent Tech Applications - https://owasp.org/www-project-top-ten-for-agent-tech-applications/
Cloud Security Alliance Report on AI Incidents - https://cloudsecurityalliance.org/research/ai-security/
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode dissects the recent Vercel breach, a supply chain attack involving third-party AI tools, OAuth vulnerabilities, and insider risks. It highlights practical steps organizations can take to enhance cybersecurity and prevent similar incidents.
Key topics
Supply chain attack involving third-party AI tools
OAuth vulnerabilities and permissions management
Best practices for environment variable security
Incident response and credential rotation strategies
Chapters
00:00 The Vercel Breach: An Overview
05:43 The Supply Chain Attack Unfolds
12:45 The Shift in Cybersecurity Paradigms
19:11 The Importance of Trust in Security
Keywords
cybersecurity, supply chain attack, OAuth, Vercal breach, AI security, cloud security, incident response, third-party risk, environment variables, credential rotation
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the groundbreaking capabilities of Anthropic's Mythos AI model, its implications for cybersecurity, and how defenders can adapt to this new threat landscape. We discuss the model's ability to autonomously identify and exploit vulnerabilities, the strategic responses from industry leaders, and the importance of critical evaluation amidst hype.
Key Topics
Chapters
00:00 The Changing Landscape of Cybersecurity
06:38 The Power of Mythos
13:18 OpenAI's Response and Different Approaches
21:46 Strategic Recommendations for Organizations
27:45 The Future of AI in Cybersecurity
Resources
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the critical relationship between identity and access management (IDAM) and holistic Governance, Risk, and Compliance (GRC) programs. Hosted by Santosh, it delves into how integrated identity management enhances security, compliance, and organizational resilience in the digital age.
Key Topics
The connection between identity and GRC
The evolution of IDAM and its role in security
Regulatory frameworks and compliance mapping
Risk management lifecycle and identity risk scoring
Future trends: Zero Trust, AI, decentralized identity
Chapters
00:00 The Importance of GRC and IDAM Integration
02:32 The Holistic Approach to GRC
07:50 The GRC Challenge Landscape
11:21 Defining Identity and Access Management (IDAM)
15:46 How IDAM Enables Governance
18:48 IDAM's Role in Risk Management
22:54 IDAM and Compliance
23:17 Compliance and IDAM: Meeting Regulatory Requirements
27:22 Maturity Levels of IDAM Programs
29:54 Common Pitfalls and How to avoid them
32:42 Key Performance Indicators for GRC and IDAM
35:19 The Future..
37:56 Conclusion: The Central Role of Identity in GRC
Keywords
IDAM, GRC, cybersecurity, identity management, compliance, risk management, zero trust, digital transformation, security architecture
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the core tools in application security - SCA, SAST, and DAST and how they form a comprehensive, shift-left security strategy to protect modern applications from vulnerabilities throughout the development lifecycle.
Key Topics
Shift-left security strategy
SCA (Software Composition Analysis)
SAST (Static Application Security Testing)
DAST (Dynamic Application Security Testing)
Chapters
00:00 Introduction to Application Security
05:08 Understanding SCA: Software Composition Analysis
08:22 Exploring SASD: Static Application Security Testing
13:23 Diving into DAST: Dynamic Application Security Testing
17:37 Integrating Security Tools for Comprehensive Protection
21:31 Conclusion and Key Takeaways
Keywords
#Application Security, #SCA, #SAST, #DAST, #Shift-Left Security, #Cybersecurity, #SoftwareVulnerabilities, #OpenSourceSecurity, #DevSecOps, #SecurityTools
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the recent security breach involving Lite LLM, a popular open-source Python library, and discusses the implications for cybersecurity in AI development. Learn how a trusted tool was exploited, the attack's mechanics, and essential security lessons for organizations.
Key Topics
Supply chain attack on Lite LLM
Multi-stage compromise via CI/CD pipeline
Malicious package injection and persistence
Lessons on dependency pinning and credential rotation
The AI tool chain as a new attack surface
Chapters
00:00 The Importance of Speed and Convenience in AI Development
04:16 The Attack Methodology
10:08 Key Lessons Learned from the Incident
Keywords
cybersecurity, AI security, supply chain attack, open source, LiteLLM, credential theft, DevSecOps, dependency management, zero trust, threat intelligence
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the critical importance of Identity Threat Detection and Response (ITDR) in modern cybersecurity. Hosted by Santosh, it covers how identity infrastructure is the most targeted layer in enterprises, the rise of identity-based attacks, and practical strategies to enhance security posture.
Key Topics
The rise of identity-based attacks and their impact
The three pillars of ITDR: visibility, detection, response
Real-world examples: SolarWinds, MGM, Striker attack
How AI is transforming cyber threats and defenses
Practical steps to assess and improve your identity security
Chapters
00:00 The Reality of Data Breaches
02:29 Understanding Identity Threat Detection and Response (ITDR)
06:58 The Urgency of ITDR in Today's Landscape
10:33 Case Study: Learning from the Striker Attack
13:18 Key Takeaways for Organizations
16:09 Identity as the New Perimeter
Keywords
cybersecurity, ITDR, identity security, data breaches, identity attacks, zero trust, cloud security, breach prevention, cybersecurity strategy
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
This episode explores the March 2026 cyber attack on Stryker Corporation, a leading medical technology company, highlighting the attack's mechanics, motives, and lessons for organizations worldwide. Learn how nation-state actors target critical infrastructure and how to defend against such destructive threats.
Key Topics
Chapters
00:00 The Calm Before the Storm
02:28 Who are Stryker Corporation
04:07 What really happened?
08:36 Understanding the Attacker: Handala
10:15 How did they do it? Technical breakdown
14:15 Lessons Learned from the Stryker Incident
17:51 Some practical best practices
22:47 Closing thoughts
Keywords
cybersecurity, critical infrastructure, nation-state attack, Wiper malware, privilege management, zero trust, threat intelligence, healthcare cybersecurity
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
Summary
In this episode of 'Secured by Design', we discuss the root cause for significant Cloudflare outage that occurred on November 18, 2025, which disrupted major internet services and highlighted the fragility of digital infrastructure. The conversation delves into the causes of the outage, its financial impact on businesses, and the lessons learned regarding cybersecurity and infrastructure reliance.
Chapters
00:00 The Financial Impact of the Cloudflare Outage
03:40 The Role of Cloudflare in Internet Infrastructure
07:16 The Technical Failure Behind the Outage
09:54 Security Implications of the Outage
12:00 Learnings and Conclusions
Cloudflare's official explaination of the outage:
https://blog.cloudflare.com/18-november-2025-outage/
#Cloudflare #outage #cybersecurity #digitalinfrastructure #security #internetreliability #digitalreliance
Let’s Stay Connected
📧 Email: [email protected]
🔗 LinkedIn: linkedin.com/in/kssantosh
From the publisher's feed
Great security solution are designed from the ground up..
Secured by Design is a podcast where Santosh shares practical insights, frameworks, and perspectives on identity security and other…