Dataset poisoning: Teaching agents to discover and misuse tools Model poisoning: Building reliable backdoors that persist and transfer What the studies show about agent backdoors Mitigation and protection guidance Securing agents beyond the model References Learn More As organizations increasingly deploy specialized AI agents, trust cannot depend solely on a model behaving as expected during evaluation or normal use.
Trained to betray: How post-training supply chain attacks hijack coding agents
About this summary. This is a short excerpt from the description that Microsoft Security published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://www.microsoft.com/en-us/security/blog/2026/11/12/trained-to-betray-how-post-training-supply-chain-attacks-hijack-coding-agents/
Source attribution: headline and facts are from Microsoft Security (microsoft.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
Microsoft researchers demonstrate hidden backdoor technique for AI agents
Microsoft researchers have demonstrated how small changes to an AI model can implant a hidden backdoor, causing an agent to execute an attacker’s command when a specific…
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
An AI model can be given a hidden backdoor by editing fewer than 10 of its rarely used neurons, without retraining the model, Microsoft researchers have shown. When a…
Detecting sleeper agents hiding in AI model neurons
Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than 10 neurons to inject a…
ARTEX AI Pentest Tool: What Security Teams Need to Know
ARTEX AI has moved from a GitHub research project to the engine behind some of the fastest-moving agentic AI cyberattacks of 2026. ARTEX is an autonomous penetration…
Inside a malicious Claude Code-branded extension and its persistent SSH backdoor
Attack chain overviewAttack chain Host reconnaissance collection SSH authorization and tunnel identities Protocol Tunneling (T1572): reverse SSH forwarding…
China-backed threat group used agentic AI pentesting tool to compromise 140 sensitive targets in 11 days
A China state-backed threat group is using ARTEX, the automated agentic AI penetration testing framework, to achieve remarkable speed, scale and success in a campaign…