HHarshal Shah·Aug 5AI Security Guardrails: Building Safe and Trustworthy AI ApplicationsLearn how AI Security Guardrails protect LLMs, AI Agents, and enterprise AI applications from prompt injection, data leakage, hallucinations.6 min read·delvingwithharshal.hashnode.dev
MManni Arora·Jan 1🛡️ Beyond Prompt Injection: The "Corrupted Intelligence" Attack and the Rise of Agentic SecurityWhy your AI Agent is only as secure as its most permissive tool—and how I hijacked one using a single search result.8 min read·agent-fight-club.hashnode.dev
MManni Arora·Dec 26, 2025Taught an AI to Attack Another AI. It Won 44% of the time — With No Backdoor.I built an AI attacker and pitted it against an HR chatbot 100 times. Even "hardened" defenses failed 44% of the time. Here's what actually works7 min read·agent-fight-club.hashnode.dev
RRuben Rotteveel·Sep 16, 2025Agent Architecture: Security & TrustLearn how to align security, trust, and accountability in multi-agent AI systems. Explore OAuth OBO, HITL review, and safe memory design.6 min read·yourenterprisearchitect.com1N
