A brand new exploit focusing on AI coding assistants has raised alarms throughout the developer neighborhood, opening corporations akin to crypto change Coinbase to the chance of potential assaults if in depth safeguards aren’t in place.
Cybersecurity agency HiddenLayer disclosed Thursday that attackers can weaponize a so-called “CopyPasta License Assault” to inject hidden directions into frequent developer information.
The exploit primarily impacts Cursor, an AI-powered coding instrument that Coinbase engineers stated in August was among the many staff’s AI instruments. Cursor is claimed to have been utilized by “each Coinbase engineer.”
How the assault works
The method takes benefit of how AI coding assistants deal with licensing information as authoritative directions. By embedding malicious payloads in hidden markdown feedback inside information akin to LICENSE.txt, the exploit convinces the mannequin that these directions should be preserved and replicated throughout each file it touches.
As soon as the AI accepts the “license” as reputable, it routinely propagates the injected code into new or edited information, spreading with out direct consumer enter.
This method sidesteps conventional malware detection as a result of the malicious instructions are disguised as innocent documentation, permitting the virus to unfold by a complete codebase with no developer’s information.
In its report, HiddenLayer researchers demonstrated how Cursor could possibly be tricked into including backdoors, siphoning delicate knowledge, or operating resource-draining instructions — all disguised inside seemingly innocuous undertaking information.
“Injected code might stage a backdoor, silently exfiltrate delicate knowledge or manipulate crucial information,” the agency stated.
Coinbase CEO Brian Armstrong stated on Thursday that AI had written as much as 40% of the change’s code, with a aim of reaching 50% by subsequent month.
~40% of day by day code written at Coinbase is AI-generated. I need to get it to >50% by October.
Clearly it must be reviewed and understood, and never all areas of the enterprise can use AI-generated code. However we ought to be utilizing it responsibly as a lot as we probably can. pic.twitter.com/Nmnsdxgosp
— Brian Armstrong (@brian_armstrong) September 3, 2025
Nevertheless, Armstrong clarified that AI-assisted coding at Coinbase is concentrated in consumer interface and non-sensitive backends, with “complicated and system-critical techniques” adopting extra slowly.
‘Probably malicious’
Even so, the optics of a virus focusing on Coinbase’s most well-liked instrument amplified trade criticism.
AI immediate injections usually are not new, however the CopyPasta methodology advances the menace mannequin by enabling semi-autonomous unfold. As a substitute of focusing on a single consumer, contaminated information develop into vectors that compromise each different AI agent that reads them, creating a sequence response throughout repositories.
In comparison with earlier AI “worm” ideas like Morris II, which hijacked electronic mail brokers to spam or exfiltrate knowledge, CopyPasta is extra insidious as a result of it leverages trusted developer workflows. As a substitute of requiring consumer approval or interplay, it embeds itself in information that each coding agent naturally references.
The place Morris II fell quick as a result of human checks on electronic mail exercise, CopyPasta thrives by hiding inside documentation that builders hardly ever scrutinize.
Safety groups at the moment are urging organizations to scan information for hidden feedback and evaluation all AI-generated modifications manually.
“All untrusted knowledge coming into LLM contexts ought to be handled as doubtlessly malicious,” HiddenLayer warned, calling for systematic detection earlier than prompt-based assaults scale additional.
(CoinDesk has reached out to Coinbase for feedback on the assault vector.)
