Finding Critical Infrastructure Bugs with Off-the-Shelf AI
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Forescout built an AI harness for embedded software, combining Joern static rules, Claude models and emulation-based validation, and ran it against 10 TCP/IP stacks. It reports 99 vulnerabilities in 90 hours, 66 of them new, at about $935 for static analysis. It rediscovered 40% of its earlier manual findings, versus nine months of manual work then. Binary targets cost six times more than source code. The harness is strongest on memory-safety bugs and weaker on logic flaws. The cost comparison excludes harness-building effort, and the figures come from Forescout alone.