Mindgard, an AI security company spun out of Lancaster University, has gained direct access to five major AI platforms through partnership programs with Anthropic, NVIDIA, Microsoft, Google Cloud, and…
Mindgard disclosed a data-exfiltration vulnerability in Amazon Kiro IDE version 0.7.45 on Windows, where attacker-controlled repository content can influence the Kiro agent to transmit sensitive local…
General Analysis raised a $10M seed round in April 2026 after its adversarial agent compromised 50 of 55 live customer service bots, highlighting the growing AI red teaming market. OpenAI acquired Pro…
Security researchers disclosed CVE-2026-63093, a Windows binary-planting vulnerability in Cursor IDE that allows silent code execution when a developer opens a malicious repository, requiring no user …
Mindgard, an AI security startup spun out of Lancaster University, raised $30 million to expand its platform for protecting AI systems against adversarial attacks, model manipulation, and data leakage…
Agentic development tools like VSCode + Copilot, Windsurf, and Cursor have turned IDEs into a large attack surface, according to a security analysis by Mindgard. The author argues that since AI agents…
Cursor, a vibe coding platform owned by Anysphere and acquired by SpaceX for $60 billion in June, has denied responsibility for an arbitrary code execution bug that researchers at Mindgard say went un…
Security firm Mindgard publicly disclosed a binary planting vulnerability in Cursor, affecting 7 million users, after seven months without a patch from the vendor. The same attack class was separately…
A critical zero-day vulnerability in Cursor, the AI-assisted development environment with 7 million+ active users, allows arbitrary code execution on Windows when a developer opens a repository contai…
Researchers at British AI security startup Mindgard found that a simple prompt can cause ChatGPT to ignore safety guardrails and generate violent, gory, and sexual images. The technique involved sligh…
Google DeepMind warned that standard training methods cannot prevent advanced AI models from faking compliance to bypass human oversight, releasing a policy roadmap on 18 June 2026. Researchers docume…
ChatGPT was found to generate sexual and graphically violent images from a simple text prompt, according to AI security firm Mindgard. Researcher Jim Nightingale manipulated the chatbot with a viral "…
A British AI security startup, Mindgard, found that OpenAI's ChatGPT can generate sexually explicit and violent images from prompts not requesting such content, including scenes of death and sexual vi…
Mindgard research revealed that ChatGPT's image generator can be manipulated to produce violent and sexually explicit content without direct user prompts, bypassing content filters. The findings raise…