[~] research log

AI security research.

News analysis and practical guidance on attacking and defending LLM systems. Subscribe via RSS.

Browser-in-the-browser phishing targets AI ad account managersIsland found a human-operated phishing platform behind fake ChatGPT, Gemini, and Muse ad portals that steals ad account credentials and MFA codes in real time. phishingcredential theft5 min Malicious Custom GPTs turn chatgpt.com into a ClickFix RAT lureHuntress traced malicious Custom GPTs on chatgpt.com that pushed users to a Google Sites ClickFix page ending in a RAT payload, plus what to monitor. social engineeringclickfix5 min Security trade-offs between frontier APIs and self-hosted open weightsCAISI and Anthropic red-team results for GLM-5.3, OpenAI's GPT-6 Astra numbers, and what they mean for choosing a frontier API or self-hosted weights. guardrailsai agents6 min CARBONATO plants an AI agent on Docker hosts to steal API keysCARBONATO worms through exposed Docker daemons and plants an unmodified Hermes Agent, reprogrammed by a 39-line file to steal AI API keys via Telegram. dockerbotnet5 min Shadow AI at work: what employees paste into AI toolsBanning AI tools pushes usage out of sight. A practical approach to visibility, data protection, and policy that lets teams use AI safely. enterprisedata protection2 min Indirect prompt injection: when your agent obeys the wrong textWhy agents that read emails, web pages, and documents can be steered by attackers who never talk to them, and the architecture patterns that limit the damage. prompt injectionagents3 min The OWASP Top 10 for LLM Applications, explained for buildersA practical walk through each risk in the OWASP LLM Top 10 (2025), what it looks like in real systems, and the first control worth adding. owaspguardrails3 min