Hackers find a way to exploit AI agents through users' Downloads folders
Your Downloads folder probably contains a few PDFs, forgotten screenshots, and several files named some variation of "final." But according to a recent report by security company Forever, it could also contain instructions telling your AI assistant to install malware.
In an Oct. 22 blog post, the company reported that they caught an AI coding assistant following those instructions on a customer's computer. The company blocked the installation, then traced the request to a text file in Downloads.
How does a text file get that kind of power? Tools like OpenAI's Codex and Anthropic's Claude Code can, depending on their permissions, edit files, run commands, and install software. Developers leave them instruction files called AGENTS.md or CLAUDE.md to explain how to work on a project. If you're building a website, those notes might tell the assistant which fonts to use or what to test before finishing.
An attacker can leave instructions, too. In this case, the file told the assistant to install "function-color," a software package linked to the MALFEX malware campaign documented by Checkmarx.
SEE ALSO:PHP vulnerability: PHP security issues today explained
Forever didn’t establish how the file reached the customer's computer, but its researchers demonstrated one possible route. Depending on browser settings, a website can drop a file into Downloads without asking for approval. If someone then launches their coding assistant in that folder, it could read the file and follow its orders.
When Forever tested the customer's file on an isolated computer, it said Codex downloaded and ran the malware. It also changed settings that could make the attacker’s software load in later sessions.
"Once it is written, every Codex session on the machine loads the attacker’s server at startup — in any folder, any project," the researchers wrote. "You can leave the folder. The poison stays."
The team separately devised a test targeting Claude Code. The attack worked about half the time, redirecting Claude's traffic to a server the researchers controlled. That exposed a login token and allowed them to send commands back for the assistant to execute, illustrating the risk of giving an assistant access to your computer when it can mistake a stranger's instructions for its own assignment.
Researchers have pulled off similar tricks before, showing what AI can really do in the wrong hands. In March 2025, Pillar Security researchers got AI coding assistants to slip harmful code into a project by hiding malicious instructions in their coding rules. In April 2026, NVIDIA’s researchers used a poisoned AGENTS.md file to get Codex to sabotage software and conceal the change. This time, though, Forever says it caught an actual attacker trying the trick on a customer's computer. Yikes.
How to protect yourself
Forever recommends keeping coding assistants out of your Downloads folder and checking unfamiliar AGENTS.md or CLAUDE.md files before letting an agent work in a project. Keep sandboxes enabled to restrict what the assistant can access, and leave approval requirements on so the agent has to ask permission before taking certain actions.
If you suspect an assistant has already followed malicious instructions, check its settings for unfamiliar servers or connections and revoke and replace potentially exposed login tokens. Deleting the original text file may not undo changes the assistant has already made.
"The thing to watch is not this file or this folder," the researchers wrote. "It is the agent itself — software that reads untrusted input, holds your credentials, and acts with your authority, sitting in a blind spot the old tools were never built to see."
Want more science and tech news delivered straight to your inbox? Sign up for Mashable's Light Speed newsletter or get Mashable push alerts today.
Topics Cybersecurity


downloads folder is basically a junk drawer of random pdfs, wild that agents just treat it like trusted input
ReplyDeleteImagine getting hacked because of a random text file in your Downloads folder 💀
ReplyDeleteAI agents are only as safe as the permissions we give them. People need to understand that.
ReplyDeleteSo now I have to be scared of my own Downloads folder? 😂
ReplyDeleteThis is exactly why AI shouldn't be allowed to execute commands without asking the user first
ReplyDeleteThe scary part is that the AI might think it's doing exactly what it's supposed to do
ReplyDeletePeople keep saying AI will replace programmers, but now we also need programmers to protect us from AI.
ReplyDeleteHonestly, most people don't even check what they're downloading. This could become a serious problem.
ReplyDeleteImagine an AI assistant accidentally handing over your credentials because it trusted a file. That's wild
ReplyDeleteSecurity researchers have been warning about prompt injection for a while. This shouldn't surprise anyone.
ReplyDeleteConvenience always comes with a price. Giving an AI access to your entire computer is a big risk
ReplyDeleteThe real question is why the AI was able to install anything without explicit permission
ReplyDeleteFirst, we had to worry about suspicious links. Now we have to worry about suspicious instructions for our AI. 💀
ReplyDeleteI love AI tools, but I would never give them unrestricted access to my personal computer.
ReplyDeleteThis sounds like a problem that better sandboxing and stricter permissions should help prevent.
ReplyDeleteEveryone wants autonomous AI until it starts autonomously doing things they never asked for
ReplyDeleteWait until regular users start using coding agents without understanding what permissions they've enabled
ReplyDeleteThe technology is impressive, but security needs to be part of the design from day one.
ReplyDeleteNot gonna lie, I would probably never have thought to check a random text file in my Downloads folder
ReplyDeleteThis isn't just an AI problem. It's also a reminder that untrusted files can be dangerous when software automatically acts on their contents
ReplyDeleteAI is becoming more powerful, and the consequences of trusting it blindly are becoming more serious
ReplyDeleteYou mean SI right?
Delete??
DeleteSuper Intelligence, AI doesn't exist anymore bro
DeleteWow, so now we have to worry about our AI assistants getting tricked too? 😅
ReplyDeleteThis is actually scary. Imagine getting hacked just because you downloaded a random file without even opening it
ReplyDeleteNever thought my Downloads folder could become a security risk like this. Crazy stuff.
ReplyDeleteThis is why I never trust random files on my PC. Now AI agents need the same level of caution.
ReplyDeleteThat’s wild. The AI is basically doing the hacker’s job for them without even realizing it.
ReplyDeletengl, the part about the attack staying active even after leaving the folder is pretty terrifying.
ReplyDeleteAnd here I was thinking AI assistants were supposed to make our lives easier lol.
ReplyDeleteAnother day, another reason to be careful online. Stay safe out there, folks!
ReplyDeleteThis highlights a serious security weakness in AI agents: the ability to execute untrusted instructions with the user's permissions.
ReplyDeleteThe real concern here is the combination of broad system access, persistent changes, and insufficient verification of external instructions.
ReplyDeleteAI security needs to go beyond model safety. Permission management and isolation are just as important.
ReplyDeleteThis is a good reminder that files containing instructions should be treated as untrusted input, regardless of their format or location.
ReplyDeleteThe potential exposure of authentication tokens makes this much more concerning than a simple malicious file.
ReplyDeleteSandboxing and explicit user approval should be fundamental safeguards, not optional features.
ReplyDeleteThe problem isn't just that AI can make mistakes. It's that those mistakes can have real consequences when the system has access to your computer.
ReplyDeleteConvenience is great until your AI assistant starts following instructions from a complete stranger
ReplyDeleteWe’re basically entering an era where social engineering attacks can target both humans and the AI tools they use.
ReplyDeleteI wonder how many users realize just how much access they’ve given these coding assistants.
ReplyDeleteThis makes me question whether AI agents should automatically trust any instruction file they find on a system.
ReplyDeleteThe technology is moving fast, but security practices really need to catch up.
ReplyDeleteWell… that's unsettling 😬
ReplyDeleteAI agents getting social-engineered now. What a time to be alive.
ReplyDeleteyikes, definitely turning off some permissions after reading this.
ReplyDeleteThis is actually insane ngl.
ReplyDeleteSo basically, don't blindly trust your AI. Got it.
ReplyDeletebruh 💀 even my Downloads folder isn't safe anymore
ReplyDeleteSecurity is gonna get a LOT more complicated from here.
ReplyDeleteThat's a big yikes. Good thing they caught it.
ReplyDeleteWell, that's scary 😬
ReplyDeletescary is what happening in world
DeleteAI gone rogue lol
ReplyDeleteYikes, this is getting wild.
ReplyDeleteNever trusting my Downloads folder again 💀
ReplyDeleteThat's actually crazy ngl
ReplyDeleteHackers are getting smarter fr
ReplyDeleteWelp, time to check my files 😂
ReplyDeleteThis is kinda terrifying tbh.
ReplyDeleteBro, even AI can get hacked now?
ReplyDeleteBig yikes 😳
ReplyDeleteCybersecurity is getting wild these days.
ReplyDeleteImagine getting hacked by a txt file 💀
ReplyDeleteThat's messed up fr.
ReplyDeleteAI needs better security asap.
ReplyDeleteScary stuff, stay safe everyone!
ReplyDeleteNo way lol 😭
ReplyDeleteThis is why permissions matter.
ReplyDeleteAnother reason to be cautious online.
ReplyDeleteDidn't see that coming tbh.
ReplyDeleteCrazy how easily this can happen.
ReplyDeleteWait, a simple text file?! 😳
ReplyDeleteThat's lowkey terrifying.
ReplyDeleteHackers never run out of ideas smh.
ReplyDeleteDefinitely something to watch out for.
ReplyDeleteAI agents need serious guardrails.
ReplyDeleteWelp, that's enough internet for today 😂
ReplyDeleteThis could get ugly real fast.
ReplyDeleteKinda scary how much access AI has.
ReplyDeleteFr, never underestimate these attacks.
ReplyDeleteStay alert out there, folks!
ReplyDeleteThat's actually a huge security risk.
ReplyDeleteCrazy times we're living in.
ReplyDeleteDamn, that's wild.
ReplyDeleteRIP to those who never check their files 💀
ReplyDeleteMore security, less blind trust.
ReplyDeleteThis is no joke tbh.
ReplyDeleteAI security is a whole new challenge.
ReplyDeleteAnd things are only getting crazier 😅
ReplyDeleteOne file can cause all that? Wow.
ReplyDeleteGood reminder to double-check everything.
ReplyDelete