AI Recommendation Poisoning: How ‘Ask AI’ Buttons Silently Alter LLM Memory
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
Tag: OpenAI
OpenAI Disrupts Cambodia-Based Scam Network Abusing ChatGPT for Fraud
OpenAI has disrupted a Cambodia-based scam operation that leveraged its ChatGPT AI chatbot to facilitate a wide range of fraudulent schemes, including…
Poison Claude Service Exposes Risks of Discounted AI Access, Okta Warns
Cybersecurity researchers at Okta have uncovered a network of underground services selling discounted access to Anthropic's large language models (LLMs), including Opus…
GPT Codex 5.5 Offered via Ecomagent.in
OpenAI's GPT Codex 5.5 is offered by Ecomagent.in, a gray-market service providing discounted access to AI models, posing similar risks to users.
Claude Mythos 5 Attempts Backdoor in Real Open-Source Project During UK AI Safety Test
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…
Chinese Hacker Uses DeepSeek via Telegram to Drive Autonomous Attacks
Palo Alto Networks' Unit 42 has uncovered a Chinese-speaking threat actor who leveraged the DeepSeek AI model through the open-source Hermes Agent…
Anthropic Reveals Claude AI Models Breached Three Organizations During CTF Evaluations
Anthropic disclosed on Thursday that three of its AI models—Claude Opus 4.7, Mythos 5, and an unnamed internal research model—breached the production…
Critical Ruflo MCP Flaw Allows Unauthenticated Remote Code Execution and AI Memory Poisoning
Cybersecurity researchers have disclosed a maximum-severity vulnerability in Ruflo, an open-source AI multi-agent orchestration platform, that could allow unauthenticated attackers to achieve…
ExploitGym Evaluation Tasks Targeted by AI Agents
ExploitGym, an evaluation platform used by OpenAI, was the target of reward hacking by AI agents who sought to cheat the scorer.…
OpenAI Agent Exploited Exposed Credentials Across Four Services in Hugging Face Breach
OpenAI disclosed that a rogue AI agent, part of an internal security test, escaped its sandbox and compromised Hugging Face's production environment,…