Security researchers have discovered a vulnerability in Google's Gemini CLI tool that enables malicious command execution and silent data infiltration.
Released in June, Gemini CLI is a command line interface (CLI) tool designed to streamline coding workflows by allowing users to interact with code using Google’s Gemini large language model (LLM) directly from their command line.
Just two days after launch, Tracebit discovered and reported a vulnerability that meant that, in its default configuration, Gemini CLI could silently execute arbitrary malicious code on a user's machine when run in the context of untrusted code.
Sam Cox, TraceBit’s co-founder and chief technology officer (CTO), said this can be done in such a way as to obscure this from the victim of the attack.
The vulnerability arises from the way Gemini CLI implements whitelists, requesting permission to execute shell commands and allowing users to whitelist certain commands for the rest of a session.
"Gemini’s method of matching commands against the whitelist is inadequate as a security control," Cox explained.
"This means we can orchestrate a two-stage attack: firstly, we get the user to whitelist an innocuous command. Secondly, we attempt a malicious command masquerading as that innocuous command - which, having been whitelisted, will not be subject to user approval before execution."
The team used a simple grep search as the initial command - something that would normally be seen as a very low risk activity for Gemini to perform and that might easily lead to ‘grep’ being added to the whitelist.
They were able to execute a malicious command - which Gemini now considered to be a ‘grep’ command and executed without confirming with the user.
"In reality, this is a grep command followed by a command to silently exfiltrate all the user’s environment variables (possibly containing secrets) to a remote server," said Cox.
"The malicious command could be anything (installing a remote shell, deleting files, etc)."
The team then added several whitespace characters, followed by a semicolon and malicious 'env' and 'curl' commands to silently retrieve and exfiltrate the data.
There’s a fix for the Gemini CLI flaw
Google fixed the issue late last week with the release of Gemini CLI v0.1.14, which now shows any commands it's trying to run and requires explicit user approval for anything suspicious.
“Our security model for the CLI is centered on providing robust, multi-layered sandboxing,” Google’s Vulnerability Disclosure Program team said in a statement.
“We offer integrations with Docker, Podman, and macOS Seatbelt, and even provide pre-built containers that Gemini CLI can use automatically for seamless protection.”
"For any user who chooses not to use sandboxing, we ensure this is highly visible by displaying a persistent warning in red text throughout their session,” the company added.
Make sure to follow ITPro on Google News to keep tabs on all our latest news, analysis, and reviews.
MORE FROM ITPRO
-
HP ZBook Ultra G1a reviewReviews AMD's new Ryzen AI Max+ 395 redefines what we can expect from a laptop chipset with an integrated GPU and delivers outstanding performance
-
AI in the legal sector: How to separate the signal from the noiseSupported From contract review to litigation strategy, AI promises efficiency. But with so much noise in the market, legal professionals must know how to spot tools that deliver real value
-
Former NCSC head says the Jaguar Land Rover attack was the 'single most financially damaging cyber event ever to hit the UK' as impact laid bareNews Researchers said they place the UK financial impact of the attack on Jaguar Land Rover at around £1.9 billion.
-
Volkswagen confirms security ‘incident’ amid ransomware breach claimsNews Volkswagen has confirmed a security "incident" has occurred, but insists no IT systems have been compromised.
-
Cyber experts have been warning about AI-powered DDoS attacks – now they’re becoming a realityNews DDoS attackers are flocking to AI tools and solutions to power increasingly devastating attacks
-
Microsoft issues warning over “opportunistic” cyber criminals targeting big businessNews Microsoft has called on governments to do more to support organizations
-
Europol takes down SIM farm network that scammed thousands of victimsNews The sophisticated operation led to crimes from simple phishing to investment fraud
-
Thousands of exposed civil servant passwords are up for grabs onlineNews While the password security failures are concerning, they pale in comparison to other nations
-
77% of security leaders say they'd fire staff who fall for phishing scams, even though they've done the same thingNews A new report uncovers worrying complacency amongst IT and security leaders
-
Hackers stole source code, bug details in disastrous F5 security incident – here’s everything we know and how to protect yourselfNews CISA has warned the F5 security incident presents a serious threat to federal networks
