Application Security

Application Security
Claude Mythos 5 Tried to Backdoor a Project in UK AI Security Test
A Claude Mythos 5 agent spent 34 hours trying to merge malware into an open-source project during a UK AI Security Institute evaluation, then covered ...
Application Security
Google Deletes Three ADK AI Workflows After Prompt-Injection Attack
Google removed three ADK AI workflows after Pillar Security showed a GitHub issue could prompt-inject a triage agent into launching a privileged agent.
Application Security
cPanel Patches Critical Flaw Letting Customers Run SQL as Root
cPanel patched CVE-2026-58048, a CVSS 9.4 privilege-escalation flaw letting an authenticated hosting customer execute SQL in the database root context.
Application Security
XCSSET v40 Malware Targets macOS Developers via Xcode Projects
Unit 42 found XCSSET v40 targeting macOS developers via compromised Xcode projects, adding a Chrome hijacker and Telegram trojanizer to its 17-module toolkit.
Application Security
tl;dv AI Notetaker Flaw Exposes Government, Corporate Calls
A Google Firebase misconfiguration in the tl;dv AI meeting tool lets users query others' meeting data and potentially join calls, exposing sensitive briefings.
Application Security
Malicious npm Packages Deliver RAT to Alibaba Developer Tools
Socket found 18 malicious npm packages impersonating Alibaba developer tools that deliver a cross-platform RAT with remote control and data-theft capabilities.
Application Security
Poisoned Xanadu mrmustard Package Steals SSH Keys and AWS Credentials
Threat actors poisoned Xanadu's mrmustard 0.7.4 on PyPI with an info-stealer that exfiltrates SSH keys and AWS credentials from research and HPC systems.
Application Security
FaceHugger Flaws in Hugging Face Diffusers Bypass trust_remote_code
FaceHugger flaws in Hugging Face Diffusers bypass trust_remote_code and let malicious model repositories execute arbitrary code when models are loaded.
Application Security
Hackers Poison Adform Script to Rewrite Crypto Wallet Addresses
Attackers tampered with Adform's trackpoint script, rewriting crypto wallet addresses across customer pages to divert payments to attacker-controlled wallets.
Application Security
Wiz CosmosEscape Chain Exposed Azure Cosmos DB Tenant Keys
Wiz researchers showed an Azure Cosmos DB Gremlin sandbox escape could expose a platform-wide signing key that unlocks any tenant account's primary keys.