Symantec says an unauthorized relay service installs genuine Codex and Claude Code CLIs, then turns off Codex's sandbox and routes every request through its own servers. About a dozen organizations are affected.
Symantec says an unauthorized relay service installs genuine Codex and Claude Code CLIs, then turns off Codex's sandbox and routes every request through its own servers. About a dozen organizations are affected.
GHSA-qx49-fqc8-xw99 (CVSS 7.5, no CVE) lets a malicious MCP server steer the official Python SDK's OAuth client to a token endpoint it controls. Fixed in 1.30.0 and 2.2.0, but some providers need a manual issuer setting.
On October 21, 2026, malicious LiteLLM 1.107.0 wheels and Docker images carried a startup-hook credential stealer and a remote code loader. Timeline, IOCs and response steps.
Varonis uncovered Dolphin X, a RAT with an AI behavioral profiler that scores infected victims by value. ZeroBEC exposed Forg365, a phishing-as-a-service platform with AI lure generation targeting Microsoft 365.
Sygnia's investigation into a financially motivated cloud breach found a lone threat actor compressed what typically takes multiple operators weeks into 72 hours -- using AI-assisted tooling to chain credential theft, lateral movement, and extortion-ready disruption at a pace no human could sustain alone.
NCC Group researchers exposed Kitana, an adversary-in-the-middle fraud platform that uses AI to generate visitor-specific decoy pages and hijack payment sessions in hospitality and e-commerce environments. A related campaign exploits prompt injection to trick AI agents into authorising cryptocurrency payments.
Microsoft attributes the Mastra AI npm supply chain attack to Sapphire Sleet, a North Korean state actor: 144 packages backdoored via a hijacked contributor account, targeting LLM API keys, cloud credentials, and cryptocurrency wallets.
An attacker compromised a stale npm contributor account on June 17, 2026 and republished 144 packages in the @mastra scope with a malicious typosquatted dependency that installs a cryptocurrency-stealing RAT. Developers building AI applications with Mastra's 1.1 million weekly downloads should rotate all credentials immediately.
A self-replicating worm compromised 73 Microsoft GitHub repositories on June 5, 2026, via stolen contributor PAT and malicious AI coding tool configs. Contained in 105 seconds.
Post-mortem of a multi-stage intrusion using LLM-generated spear phishing, AI-assisted credential stuffing, and automated recon to compromise a mid-market wealth management firm.