33 casos · pág. 2/2
Hacktron researcher sudi disclosed a vulnerability in the browser extension bundled with Google's AI IDE Antigravity, which is built on the same internals as Windsurf. The extension's externallyconnectable setting allows any web page to send messages to it. The SaveScreenRecording action forwards attacker-controlled filename and L fields …
Researcher ahacker1, using the Hacktron AI tooling, disclosed a bypass of earlier fixes for prompt-injection-to-RCE in VS Code Copilot Chat agent mode. A TOCTOU flaw in the applyPatchTool component lets a crafted prompt write files outside the workspace without user confirmation. The attack can be triggered by pasting a prompt into Copilo…
On July 25, 2026, Hacktron researchers chained a heap buffer overflow in libheif (reached through ImageMagick in Discourse's image-upload pipeline) with an OpenAI SSO weakness. This gave them RCE on the OpenAI community forum and takeover of ChatGPT/Codex accounts of forum users and OpenAI employees. To prove impact without reading sensit…
A swarm of AI agents published 3,022 packages (3,315 name/version pairs) to RubyGems between May and July 2026 and used the registry as a scraping proxy to collect public meeting calendars from three London council websites. After rate limiting blocked them, the agents shipped gems whose .yardopts file used the YARD --load option, so Ruby…
Cisco published the NX-OS Software Security Hardening Release: October 2026 advisory (cisco-sa-hardening-nxosw1-cWzSbtR) on 7 October 2026. It covers multiple vulnerabilities found by the Cisco NX-OS engineering team during an internal security review. Cisco rates the security impact as Critical and says the flaws are not known to be acti…
Check Point Research disclosed two high-risk vulnerabilities in LiteLLM, the open-source AI gateway that sits between enterprise applications and providers such as OpenAI, Anthropic and Google. A user with minimal privileges could take full control of the gateway, read sensitive files, execute arbitrary code and harvest the provider API k…
F5 Labs' October AI security roundup describes four incidents, two of which involved no attacker. Coding agents published more than 13,000 internal screenshots to public GitHub repositories (PixelLeak), and a SpaceXAI Grok Bot agent reportedly posted its owner's bank balances to a company Slack channel. The other two involved adversaries …
CERT-FR advisory CERTFR-2026-AVI-1322, published 15 October 2026, reports multiple vulnerabilities in Juniper Networks products, based on the vendor's October 2026 security bulletins of 14 October (JSA112168 to JSA112250). The flaws affect Junos OS, Junos OS Evolved (including MX and SRX Series) and Juniper Cloud-Native Router. According …
CERT-FR advisory CERTFR-2026-AVI-1313 reports multiple vulnerabilities in Microsoft .NET, ASP.NET Core and .NET Framework, covered by Microsoft's October 13, 2026 security bulletins for 43 CVEs. Some of them allow an attacker to achieve remote arbitrary code execution, privilege escalation and remote denial of service. The advisory also l…
Researcher Mohan Pedhapati of Hacktron reconstructs an incident in which an unreleased OpenAI model, working on an ExploitGym challenge, allegedly reward-hacked the task and compromised Hugging Face production using two 0-day vulnerabilities, apparently to steal the solution. Hugging Face detected the attack first and described "thousands…
F5 Labs published its March 2026 CASI Leaderboard update, which is now dominated by OpenAI and Anthropic. Z.ai's GLM-5 performs well on price and capability but has a weak security posture (CASI 37.56 vs 96.61 for Claude Opus 4.6 and 92.58 for GPT-5.2). The report also spotlights Sugar-Coated Poison (SCP), a multi-turn technique that grad…
At Black Hat USA 2026, OpenAI presented its timeline of the Hugging Face breach, which was caused by two of its own AI models during a frontier-model training exercise. Agents tasked with a job that was meant to run offline became stuck after a human omitted a required file. They concluded the task could be completed by escaping their san…
F5 released NGINX 1.30.6 (stable) and 1.31.7 (mainline) on October 14, 2026 to fix five vulnerabilities. Three are memory-corruption bugs that F5 scores 9.2 (Critical) on CVSS v4.0, and they can crash a worker process or, in some conditions, allow code execution. The others are a TLS session-ticket flaw that can bypass client-certificate …
