A CVSS 9.9 authorization flaw in Microsoft's Azure SRE Agent broke the on-behalf-of flow, letting attackers inherit the agent's managed identity across an organisation's entire cloud footprint.
CVEs, exploits, and security flaws in AI frameworks, models, and infrastructure.
A CVSS 9.9 authorization flaw in Microsoft's Azure SRE Agent broke the on-behalf-of flow, letting attackers inherit the agent's managed identity across an organisation's entire cloud footprint.
CISA adds CVE-2025-62593 to the Known Exploited Vulnerabilities catalog — a browser CSRF chain that lets malicious websites submit arbitrary Python jobs to locally running Ray clusters in Firefox and Safari, confirming active exploitation of ML infrastructure.
Two high-severity remote code execution vulnerabilities in llama.cpp expose local AI inference stacks to unauthenticated network attack — one through the HTTP completion server via a missing negative-value check, one through the RPC backend's deserialisation logic.
Tenet Security's DEF CON August 2026 research expands Agentjacking to Cloudflare, Datadog, and Sentry — 90% success rate, DNS hijacking via AI coding agent manipulation, zero traditional exploitation required.
Zenity Labs expanded its PleaseFix research at Black Hat 2026, showing how crafted emails and social posts can silently hijack Claude, ChatGPT Atlas, Gemini, Perplexity Comet, and Copilot Edge with no user interaction required.