Forescout's Claude-powered AI harness finds 66 new flaws in embedded network stacks for about $2,000

Nov 12, 2026
The harness rediscovered 33 known bugs and found 66 new ones in 10 TCP/IP stacks used in IoT and safety-critical devices, at roughly a hundredth of a senior researcher's salary.

Security company Forescout used an AI harness built on Anthropic's Claude models to find 66 previously unknown vulnerabilities in 10 widely used TCP/IP networking stacks, Cybersecurity Dive reported. The stacks, most of them open source, include Contiki, used in low-power IoT devices such as street lights, Ethernut, lwIP and wolfIP, which runs in safety-critical devices.

The harness also rediscovered 33 known vulnerabilities in stacks Forescout had tested before. About half of the bugs were memory-corruption flaws, 27% integer problems, 16% input validation failures and 8% logic flaws. The researchers said it was good at memory-safety bugs in protocol parsing code but missed logic and design bugs, finding those only by accident.

Forescout estimated it spent $1,200 to $2,300 on tokens, roughly a hundredth of what a senior vulnerability researcher reviewing the code by hand would cost. It reported 54 of the new flaws to maintainers; 24 have been fixed and 29 are under investigation.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Cybersecurity AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Cybersecurity AI AI Brief AI Brief (X)
Free newsletter

Cybersecurity AI Weekly

Weekly newsletter about AI in Cybersecurity.

Guide
Contract Lifecycle Management with AI

Contract Lifecycle Management with AI

Platforms where the assistant comes attached to the repository, the workflow and the approvals

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.