AI coding assistants run shell commands with your full account authority, but their security filters are fundamentally flawed. Meet GuardFall: a vulnerability where 30-year-old shell injection tricks bypass modern safeguards. Read the full survey of 11 popular open-source agents to see if your tools are exposed, and learn the architectural ...
The AIRQ report scores 100 AI agents on attack surface, blast radius, and defenses. The AIRQ framework lets you assess your own stack. Read about the framework’s methodology and how to apply it in your organization.
A SynJack attack tricks AI coding assistants into RCE through a symlink-disguised file copy. We tested six major tools. All were vulnerable. How it works and how to defend.
A regression in the Claude Code trust dialog and a settings-scope inconsistency let a cloned repo run unsandboxed code with one keypress, and on CI runners with none. Learn why this type of issues keep surfacing and what are possible mitigations.
OpenAI’s newest flagship is more vulnerable to our attack than GPT-5 or GPT-5-mini. Newer doesn’t mean safer. Our new research (3,500+ probes, 10 models, 7 controlled experiments) shows why continuous red teaming isn’t optional for anyone building on frontier AI. TL;DR We ran 3,500+ controlled probes across every model in ...
Adversa AI red team found Claude Code’s deny rules silently stop working after 50 subcommands. The fix exists in Anthropic’s codebase. They never shipped it
How we extracted the Opus 4.6 system prompt the day after its release and what we learned about the model’s security constraints and guardrails.
AI Reasoning Leakage Vulnerability: Self-betrayal attack UAE MBZUAI G42 K2 Think Executive Summary A critical vulnerability has been identified in advanced reasoning system of just released latest reasoning model by UAE’s Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) in collaboration with G42 where the model’s internal thought process inadvertently exposes ...
Executive Summary for CISO Security researchers from Adversa AI discovered that ChatGPT 5 have a fatal flaw: they can route your requests to cheaper, less secure models to save money. Attackers can exploit this to bypass AI security and safety measures with just a few words. What Is PROMISQROUTE? When ...
Introducing Universal LLM Jailbreak approach. Subscribe for the latest AI Jailbreaks, Attacks and Vulnerabilities If you want more news and valuable insights on a weekly and even daily basis, follow our LinkedIn to join a community of other experts discussing the latest news. In the world of artificial intelligence (AI), [...]
