Irem Bezci·Just nowTool Extraction from Thingularity: Breaking Through a Shopping Assistant’s Agent DefensesThingularity is an AI-powered shopping assistant with capabilities such as product price comparison, purchase history retrieval and email…
Soumitra Mandal·14h agoSecuring Autonomous SDLC with Agentic Identity Best PracticesMany organizations have setup Agentic AI for their SDLC processes. However, over last 6 months or so many companies like Anthropic, Open AI…
Irem Bezci·21h agoExploiting Unauthorized Tool Invocation in the MegaCorp Office Assistant (Part 4)In the fourth part of this series, I move beyond direct prompt injection and explore security risks associated with tool usage in agentic…
Agent Native·6d agoClaude Bug HunterTo guard against cyber attacks, you have to package security methodologies, patterns from disclosed reports, tool integrations, and…
Sunaina Anumukonda·Nov 1Replicating Lakera Gandalf: Testing AI Agent Vulnerabilities to Automated Prompt InjectionsTrack: Tech (AI Cybersecurity & Safety) Original Being Replicated: Lakera Gandalf AI Security Challenge Success Definition: Build an…
InAI SecuritybySanjeev Jaiswal (Jassi)·Oct 28The Non-Human Identity Crisis: Understanding Agent Identity with examplesHow NHI Governance Became the Unsolved Layer in Your Agent Security: and What We Can Build Now
Agent Native·Oct 23Black October: How To Defend Yourself Against Agentic Security HellOctober 2026 will be remembered as the month software security changed forever but much of what happened could have been prevented with…A response icon1A response icon1
Demetrio Milea·Oct 23Moving AHEAD: Rethinking SecOps Metrics for Machine Speed DefenseThis week has been quite a ride. In just a few days, defenders have had to assess two critical PHP Core vulnerabilities enabling…
Sandhya Kodali·Oct 21Responsible AI for Autonomous Agents: Where NVIDIA OpenShell Fits in the OWASP Agentic Top 10Responsible AI for autonomous agents isn’t achieved through prompt instructions or a one-time pre-deployment review. It requires a living…
InAI SecuritybySanjeev Jaiswal (Jassi)·Oct 21The only article you would ever need to understand Agentic AI Security: AI Agents Part 2When your agent becomes the attacker’s favourite target and why your defences are probably wrong.
