Forescout
Device-security company whose research lab studies IoT, OT and embedded-network flaws; in 2026 it showed an off-the-shelf AI harness finding dozens of TCP/IP stack bugs.
Forescout sells asset-inventory, network-access and IoT/OT security products and runs a research lab focused on connected and embedded devices. Its Project Memoria, which began in 2020 and took 18 months, found almost 100 vulnerabilities in embedded TCP/IP stacks. In November 2026 it revisited that work with an AI harness built on Claude models and found 66 new bugs for a token bill of a few thousand dollars (Forescout AI harness finds 66 TCP/IP stack bugs).
Timeline
Every dated event in the wiki that involves Forescout, newest first.
Forescout built an AI harness on Claude models for embedded software and ran it on 10 TCP/IP stacks used in IoT and industrial devices (Contiki, Ethernut, lwIP, wolfIP and others). It rediscovered 33 known bugs and found 66 new ones, about half memory corruption, for an estimated $1,200-$2,300 in tokens (Forescout's figure). It reported 54; Cybersecurity Dive counts 24 fixed so far.
Connections
Forescout and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →
What links here
Cited by
Cited as a source by 1 timeline events.
2 articles cite Forescout as a source: AI and CVEs: latent flaws, now exploitable · Forescout AI harness finds 66 TCP/IP stack bugs