A brand new exploit focusing on AI coding assistants has raised alarms throughout the developer group, opening firms reminiscent of crypto trade Coinbase to the danger of potential assaults if intensive 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 recordsdata.
The exploit primarily impacts Cursor, an AI-powered coding device that Coinbase engineers mentioned 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 approach takes benefit of how AI coding assistants deal with licensing recordsdata as authoritative directions. By embedding malicious payloads in hidden markdown feedback inside recordsdata reminiscent of 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 legit, it routinely propagates the injected code into new or edited recordsdata, 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 via a complete codebase and not using a 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 venture recordsdata.
“Injected code might stage a backdoor, silently exfiltrate delicate knowledge or manipulate vital recordsdata,” the agency mentioned.
Coinbase CEO Brian Armstrong mentioned on Thursday that AI had written as much as 40% of the trade’s code, with a objective of reaching 50% by subsequent month.
~40% of every 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 needs to be utilizing it responsibly as a lot as we presumably 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.
‘Doubtlessly malicious’
Even so, the optics of a virus focusing on Coinbase’s most popular device amplified trade criticism.
AI immediate injections should not new, however the CopyPasta technique advances the menace mannequin by enabling semi-autonomous unfold. As a substitute of focusing on a single consumer, contaminated recordsdata grow to be 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 e 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 recordsdata that each coding agent naturally references.
The place Morris II fell quick as a consequence of human checks on e mail exercise, CopyPasta thrives by hiding inside documentation that builders hardly ever scrutinize.
Safety groups at the moment are urging organizations to scan recordsdata for hidden feedback and evaluation all AI-generated modifications manually.
“All untrusted knowledge getting into LLM contexts needs 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.)
