Anthropic on Friday disclosed that Project Glasswing has helped uncover more than 10,000 high- or critical-severity vulnerabilities across some of the most “systemically” important software across the world since the cybersecurity initiative went live last month. Project Glasswing is an effort led by the artificial intelligence (AI) company, as part of which a small set…
Tag: uncover
AI, Global Security News
Malicious npm Dependency Linked to AI Assisted Commit Targets Crypto Wallets
Researchers uncover a malicious npm dependency linked to an AI‑assisted code commit that steals sensitive data and exposes crypto wallets
Global Security News
BlackFile Group Targets Retail and Hospitality with Vishing Attacks
Researchers uncover a new data theft and extortion group dubbed “BlackFile”
AI, Cybersecurity, Exploits, Global Security News
Hackers Use Hidden Website Instructions in New Attacks on AI Assistants
Cybersecurity researchers at Forcepoint uncover new indirect prompt injection attacks that use hidden website code to exploit AI assistants like GitHub Copilot.
Global Security News, Risk Management
Foxit flags hidden security risks in PDFs with new tool
Foxit Software introduced a new capability designed to uncover hidden security risks inside PDFs as part of its latest PDF Editor 2026.1 release for Windows and macOS. The update is led by PDF Action Inspector, a new tool that proactively scans documents for embedded JavaScript and self-modifying behaviors — threats that can bypass redaction, expose…
AI, Apps, Exploits, Global Security News, Risk Management
Novee introduces autonomous AI red teaming to hunt LLM vulnerabilities
Novee today introduced AI Red Teaming for LLM Applications for its AI penetration testing platform, designed to uncover security vulnerabilities in LLM-powered applications before attackers can exploit them. Enterprises are deploying AI-enabled software, from customer-facing chatbots to internal copilots and autonomous agents, and security teams are now facing a new class of risks, including prompt…
AI, Exploits, Global Security News
Threat Actor Exploits Flaws and Uses Elastic Cloud SIEM to Manage Stolen Data
Huntress researchers uncover campaign exploiting vulnerabilities to steal data using Elastic Cloud as a data hub
AI, Global Security News
PleaseFix Flaw Lets Hackers Access 1Password Vault via Comet AI Browser
Researchers at Zenity Labs uncover PleaseFix flaws in Perplexity’s Comet browser. See how zero-click calendar invites allow AI agents to steal 1Password credentials and personal files.
AI, Exploits, Global Security News
Spam Campaign Abuses Atlassian Jira, Targets Government and Corporate Entities
We uncover how a campaign used Atlassian Jira Cloud to launch automated and targeted spam campaigns, exploiting trusted SaaS workflows to bypass security controls.