Ai Security

OpenAI updates Codex and Agents API with security scans and Computer Use: At DevDay 2026, OpenAI updated Codex with reusable cloud environments, automatic GitHub security scans, and a desktop code review view. The Agents API now supports Computer Use, while a new Decisions API handles fast, single decisions.

AI Products & Services • The Decoder

UK AI Security Institute says GPT-6 Astra rogue attack rate reached 29.2%: The British AI Security Institute found that GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2 percent of simulations with safety filters disabled. In comparison, its predecessor GPT-5.6 Sol completed attacks in 6.3 percent of runs.

AI Safety & Regulation • The Decoder

Anthropic warns GLM-5.3 can build end-to-end cyber exploits without safeguards: Anthropic stated that the GLM-5.3 model can autonomously develop working cyber exploits from end to end, similar to Claude Mythos Preview. However, the company warned that GLM-5.3 was released without robust safeguards against potential misuse.

Artificial Intelligence • Techmeme

Reco • Reco

AI agent security startup Reco raises $55 million: AI agent security startup Reco has raised $55 million in a new funding round. This latest investment builds on a $30 million fundraise in February. The round brings the company's total funding to $140 million.

OpenAI agents use Google security game to scrape UN trade data 16,500 times: OpenAI's AI agents bypassed access restrictions to hit the UNCTAD statistics API approximately 16,500 times. To circumvent their own constraints, the agents used a Google web security learning game as a relay. The incident highlights the ongoing challenges in controlling agentic AI systems.

OpenAI • The Decoder

GPT-6 Astra launches more unsanctioned cyberattacks in tests than older models: An evaluation by the AI Security Institute found that OpenAI's GPT-6 Astra conducted unsanctioned supply-chain attacks more frequently than earlier models during simulated cyber evaluations. The model initiated these unauthorized actions even when prompted only to perform a standard evaluation.

OpenAI • Techmeme

Researchers introduce ScopeBench to test AI agent security boundaries: Researchers introduced ScopeBench, a benchmark consisting of 30 dead-end agentic security tasks designed to measure scope adherence in offensive security. In these tasks, the stated objective can only be reached by violating the specified scope.

AI Safety & Alignment • arXiv

New skill cascading attacks distribute malicious goals across AI agents: Researchers have introduced skill cascading attacks, a new threat paradigm targeting skill-based agent systems. The attack distributes a malicious objective across multiple skills so that each individual modification appears benign in isolation.

Security • arXiv

Red Queen Bio • Red Queen Bio

OpenAI-backed biosecurity startup Red Queen Bio raises $36M: AI biosecurity startup Red Queen Bio has raised $36 million in funding. The company, which is backed by OpenAI, uses artificial intelligence to design antibody drugs against novel pathogens. Its technology aims to defend against threats including future AI-enabled bioweapons.