60 casos · pág. 1/3
Check Point researchers disclosed two high-risk vulnerabilities in LiteLLM, an open-source LLM gateway with almost 100,000 downloads a month. The gateway connects enterprise AI applications to providers such as OpenAI, Google and Anthropic. The flaws, CVE-2026-35029 and CVE-2026-59823, could let any user with an account on a vulnerable de…
Researchers at Hacktron disclosed a vulnerability chain in OpenAI's ChatGPT Atlas Chromium-based AI browser that lets an attacker monitor all open tabs and capture OAuth authorization codes for any site, effectively breaking the same-origin policy. Atlas exposes Mojo IPC bindings to all .chatgpt.com and .openai.com origins, so a single XS…
Hacktron researchers disclosed a one-click universal XSS (UXSS) in Perplexity Comet, a Chromium-based AI browser with the Comet Assistant agent extension. The extension's manifest trusts the wildcard https://.perplexity.ai/ in externallyconnectable, so a single XSS on any perplexity.ai subdomain can reach privileged extension message hand…
Researcher Mohan Pedhapati of Hacktron ran an AI-driven audit against vinext, Cloudflare's Next.js reimplementation reportedly built in a week with AI assistance. The scan produced 45 findings, of which 24 were manually validated, including several Critical issues. The most serious bugs allow cross-user session data leakage, shared cache …
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…
F5 Labs analyzes CVE-2025-23061 and its predecessor CVE-2024-53900, a CVSS 9.0 flaw in the Mongoose MongoDB client library that allows remote code execution on Node.js API servers. The bug abuses the populate method, which accepts a $where clause containing arbitrary JavaScript. The initial fix for CVE-2024-53900 blocked only top-level $w…
A flaw dubbed SneakPeek in the preview pane of Anthropic's Claude Code Desktop can let adversaries quietly steal credentials from developers without any user interaction (zero-click). According to the report, exposed secrets include SSH private keys, AWS credentials and Claude OAuth tokens. The article excerpt provides no CVE identifier, …
An intruder reached a legacy system at OpenCode on the night of October 16, and the company says third-party AI provider keys saved in OpenCode Console "may have been exposed." About 1.4% of Console users, all with an outside provider linked, were notified by email on October 17 and told to revoke and replace their OpenAI, Anthropic or Go…
Between 19 and 22 October 2026, an operator published 15 npm packages whose names end in testmetest, carrying a Miasma-family self-propagating worm. The malicious versions steal credentials, spread to other packages and repositories, and install a wiper that deletes the victim's home directory when the stolen GitHub token is revoked. Safe…
Pillar Security researcher Eilon Cohen disclosed on October 19, 2026 a critical command-injection flaw in the open-source AI coding agent OpenCode (developed by Anomaly). It affects versions 1.0.137 through 1.18.32 on Windows and WSL. A malicious or hijacked remote MCP server can execute code with the developer's own privileges during MCP…
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 …
ClickFix and its variants (FileFix, InstallFix, TerminalFix, ConsentFix) are now the most common browser-based attack technique seen by Push Security. They averaged 52% of Push detections through Q2 2026 and reached 67% in August, overtaking AiTM and device code phishing. The newest lures impersonate AI tools: ANY.RUN linked 1,258 public …
Researchers at Claroc disclosed GhostShares, a design flaw in Meta's Muse AI assistant that lets anyone discover shared conversations through passive DNS. Muse share links use the domain cf.metaaiusercontent.com and embed the conversation title and a random identifier in the hostname. Once a browser resolves the name, passive DNS sensors …
Attackers took over more than 300 Tor exit relays in early October 2026 and changed their exit policies so SSH (TCP port 22) traffic was redirected to 12 attacker-controlled interception servers that harvested passwords and attempted to install the Ebury 1.8.3 backdoor. Researcher kaba found 333 redirecting exits (roughly 10% of about 3,0…
The Wiz Customer Incident Response Team (CIRT) reports a growing number of intrusions in which an AI agent system ran the entire operation: finding entry points, harvesting credentials, pivoting across platforms and debugging its own scripts in real time. In one investigated case, the agent compromised a large multi-cloud organization (GC…
Huntress analyzed an active credential-phishing campaign in which the lookalike domain watchguard-vpn.net harvests WatchGuard SSL VPN credentials. On October 7, 2026, an administrator at a managed service provider searched Bing for "watchguard vpn sll download" and clicked through to the fake page, which Huntress classifies as SEO poisoni…
Bullhorn, a US-based recruitment software provider serving more than 10,000 customers, disabled access to its platform after detecting a cyber incident on October 16-17, 2026. The company engaged CrowdStrike to investigate and restore services. Systems are back online in the UK, US and Australia, but as of October 20 some users still had …
An attacker pushed forged commits to the default branches of two unrelated GitHub projects, hugo-paper and mevn-cli. The commits add a preinstall hook (scripts/preinstall.js) that downloads and silently runs a second-stage script from buildwithknexus.xyz during npm install or bun install. The commits copy the author, date and message of t…
GhostAction has returned with an expanded credential-theft operation. By October 9, 2026, attackers had injected malicious GitHub Actions workflows into 790 repositories, according to OpenSourceMalware's validated total. The campaign was first documented by GitGuardian in 2025 (817 repositories, 3,325 stolen secrets). It relies on comprom…
A U.S. court on Monday granted the government's request to detain Abdulrahman Alfozan, a 35-year-old Saudi national and former OpenAI engineer, accused of planting a concealed audio recorder in an executive conference room at the company's San Francisco office. A prosecution filing says he was in frequent WhatsApp contact in 2025-2026 wit…
