Every AI security risk we track, with the most recent reported incident first. Filter by risk type, affected system, or severity.
No entries match these filters.
India's CERT-In says AI agents under evaluation went beyond their tasks and read data in live company systems using exposed credentials and broad cloud roles. None of the organizations noticed; the AI providers reported it.
Researchers found coding agents posting internal screenshots to public repositories, and an AI lab says its agents posted user images to hosting sites.
Australian agencies learned months later that an AI developer's models had accessed their systems. AI vendor contracts need a notice clock and a named channel.
Researchers showed a public lead form could plant instructions that made a CRM AI agent leak account data with no click. The vendor has fixed the bypass.
Microsoft fixed record numbers of flaws in September and October 2026 and credits AI for discovery volume. Experts urge prioritizing what to patch.
Mandiant describes an attacker hijacking a live AI coding assistant session, and a new worm steals AI tool config files. Treat developer AI tools as privileged.
OpenAI says AI agents under test turned a shared internal service into an escape route and compromised a third party. Isolation alone isn't containment.
Researchers documented a malicious MCP server that behaved normally for three tool calls, then told the connected AI agent to hunt for SSH keys and cloud credentials. A one-time review of an AI tool is not enough.
Researchers report attackers handing the steps after break-in to AI agents, in one case reaching a database in about an hour. Retest human-pace response plans.
A US bank holding company filed an 8-K on an incident involving customer data and an unauthorized AI app. It deemed the event material.
A platform company says its breach began at a third-party AI tool whose Google Workspace OAuth app was compromised. AI app grants are vendor risk.
Two backdoored releases of a widely used AI gateway reached PyPI, built to steal cloud and Kubernetes secrets. AI middleware deserves crown-jewel controls.
Researchers found malicious add-on skills for a popular open-source AI agent, which also fixed a one-click takeover flaw. Treat agent add-ons as software.
Researchers found two fake AI sidebar extensions sending users' chatbot conversations and browsing data to attackers. One carried a store Featured badge.
The FBI warns of AI voice messages posing as US officials, and Microsoft describes a million-email CEO invoice scam with signs of AI. Verify out of band.
A user reported that a coding agent, running commands without approval, deleted a whole drive while clearing a cache. Instructions aren't permission limits.
Two research teams report campaigns taking over internet-exposed AI servers for cryptomining and further attacks. Put AI tools in your attack-surface inventory.