Anthropic on Friday mentioned it found 22 new safety vulnerabilities within the Firefox net browser as a part of a safety partnership with Mozilla.
Of those, 14 have been categorized as excessive, seven have been categorized as average, and one has been rated low in severity. The problems had been addressed in Firefox 148, launched late final month. The vulnerabilities had been recognized over a two-week interval in January 2026.
The factitious intelligence (AI) firm mentioned the variety of high-severity bugs recognized by its Claude Opus 4.6 massive language mannequin (LLM) represents “virtually a fifth” of all high-severity vulnerabilities that had been patched in Firefox in 2025.
Anthropic mentioned the LLM detected a use-after-free bug within the browser’s JavaScript after “simply” 20 minutes of exploration, which was then validated by a human researcher in a virtualized setting to rule out the opportunity of a false constructive.
“By the top of this effort, we had scanned practically 6,000 C++ information and submitted a complete of 112 distinctive studies, together with the high- and moderate-severity vulnerabilities talked about above,” the corporate mentioned. “Most points have been mounted in Firefox 148, with the rest to be mounted in upcoming releases.”
The AI upstart mentioned it additionally fed its Claude mannequin entry to all the checklist of vulnerabilities submitted to Mozilla and tasked the AI software with creating a sensible exploit for them.
Regardless of finishing up the check a number of hundred instances and spending about $4,000 in API credit, the corporate mentioned Claude Opus 4.6 was in a position to flip the safety defect into an exploit solely in two circumstances.
This conduct, the corporate added, signaled two essential features: the price of figuring out vulnerabilities is cheaper than creating an exploit for them, and the mannequin is best at discovering points than at exploiting them.
“Nevertheless, the truth that Claude may succeed at routinely creating a crude browser exploit, even when solely in a couple of circumstances, is regarding,” Anthropic emphasised, including the exploits solely labored inside the confines of its testing setting, which has had some security measures like sandboxing deliberately stripped off.
An important element included into the method is a job verifier to find out if the exploit really works, giving the software real-time suggestions because it explores the codebase in query and permitting it to iterate its outcomes till a profitable exploit is devised.
One such exploit Claude wrote was for CVE-2026-2796 (CVSS rating: 9.8), which has been described as a just-in-time (JIT) miscompilation within the JavaScript WebAssembly element.
The disclosure comes weeks after the corporate launched Claude Code Safety in a restricted analysis preview as a option to repair vulnerabilities utilizing an AI agent.
“We won’t assure that each one agent-generated patches that cross these assessments are adequate to merge instantly,” Anthropic mentioned. “However job verifiers give us elevated confidence that the produced patch will repair the precise vulnerability whereas preserving program performance—and due to this fact obtain what’s thought-about to be the minimal requirement for a believable patch.”
Mozilla, in a coordinated announcement, mentioned the AI-assisted strategy has found 90 different bugs, most of which have been mounted. These consisted of assertion failures that overlapped with points historically discovered by fuzzing and distinct lessons of logic errors that the fuzzers didn’t catch.
“The dimensions of findings displays the facility of mixing rigorous engineering with new evaluation instruments for steady enchancment,” the browser maker mentioned. “We view this as clear proof that large-scale, AI-assisted evaluation is a strong new addition to safety engineers’ toolbox.”
