JJebitok·Sep 8LLM Pentesting (TryHackMe)Link to the challenge on TryHackMe: LLM Pentesting Introduction You are on day three of an authorised penetration test for Hartwell, a B2B SaaS company whose employee portal includes an internal AI as26 min read·sharonjebitok.com
VVũ Nhật Lâm·Aug 6Agent Data Injection: Fooling AI Agents With the Data They Already TrustRisk Summary You ask a web agent to summarize the reviews on a product page. A fake review planted by an attacker makes it click "Buy Now" instead, and an order goes through. No malware, no phishing,20 min read·blog.fiscybersec.com
VVũ Nhật Lâm·Jun 23Gemini's Secret Affair: Notification-Based Prompt Injection and the Fake Context Alignment TechniqueA single WhatsApp message from an unknown number is enough to turn the Gemini voice assistant into an attacker's tool — opening the smart windows in a victim's home, live-streaming their video over Zo12 min read·blog.fiscybersec.com
JJebitok·May 9RAG Security Fundamentals (TryHackMe)Introduction Retrieval-Augmented Generation (RAG) allows language models to use external documents when answering questions. Instead of relying solely on training data, a RAG system retrieves relevant13 min read·sharonjebitok.com
JJebitok·May 8Securing AI Systems (TryHackMe)Introduction TryTrainMe's engineering team has built TryAssist, an AI-powered code review assistant that analyses pull requests, queries internal documentation, and connects to the CI/CD pipeline. Bef10 min read·sharonjebitok.com
TTatiane Pimenta Leal·Mar 1MITRE ATLAS and OWASP | API Security in the Age of LLMExploring AI/LLM API security, model inference attacks, prompt injection risks, API management, and mitigation with MITRE ATLAS and OWASP frameworks.5 min read·tatianepimentaleal.hashnode.dev
