Krebs on Security

Anti-DDoS Firm Heaped Attacks on Brazilian ISPs

April 30, 2026

A Brazilian tech firm that specializes in protecting networks from distributed denial-of-service (DDoS) attacks has been enabling a botnet responsible for an extended campaign of massive DDoS attacks against other network operators in Brazil, KrebsOnSecurity has learned. The firm’s chief executive says the malicious activity resulted from a security breach and was likely the work of a competitor trying to tarnish his company’s public image.

An Archer AX21 router from TP-Link. Image: tp-link.com.

For the past several years, security experts have tracked a series of massive DDoS attacks originating from Brazil and solely targeting Brazilian ISPs. Until recently, it was less than clear who or what was behind these digital sieges. That changed earlier this month when a trusted source who asked to remain anonymous shared a curious file archive that was exposed in an open directory online.

The exposed archive contained several Portuguese-language malicious programs written in Python. It also included the private SSH authentication keys belonging to the CEO of Huge Networks, a Brazilian ISP that primarily offers DDoS protection to other Brazilian network operators.

Founded in Miami, Fla. in 2014, Huge Networks’s operations are centered in Brazil. The company originated from protecting game servers against DDoS attacks and evolved into an ISP-focused DDoS mitigation provider. It does not appear in any public abuse complaints and is not associated with any known DDoS-for-hire services.

Nevertheless, the exposed archive shows that a Brazil-based threat actor maintained root access to Huge Networks infrastructure and built a powerful DDoS botnet by routinely mass-scanning the Internet for insecure Internet routers and unmanaged domain name system (DNS) servers on the Web that could be enlisted in attacks.

DNS is what allows Internet users to reach websites by typing familiar domain names instead of the associated IP addresses. Ideally, DNS servers only provide answers to machines within a trusted domain. But so-called “DNS reflection” attacks rely on DNS servers that are (mis)configured to accept queries from anywhere on the Web. Attackers can send spoofed DNS queries to these servers so that the request appears to come from the target’s network. That way, when the DNS servers respond, they reply to the spoofed (targeted) address.

By taking advantage of an extension to the DNS protocol that enables large DNS messages, botmasters can dramatically boost the size and impact of a reflection attack — crafting DNS queries so that the responses are much bigger than the requests. For example, an attacker could compose a DNS request of less than 100 bytes, prompting a response that is 60-70 times as large. This amplification effect is especially pronounced when the perpetrators can query many DNS servers with these spoofed requests from tens of thousands of compromised devices simultaneously.

A DNS amplification attack, illustrated. It shows an attacker on the left, sending malicious commands to a number of bots to the immediate right, which then make spoofed DNS queries with the source address as the target's IP address.

A DNS amplification and reflection attack, illustrated. Image: veracara.digicert.com.

The exposed file archive includes a command-line history showing exactly how this attacker built and maintained a powerful botnet by scouring the Internet for TP-Link Archer AX21 routers. Specifically, the botnet seeks out TP-Link devices that remain vulnerable to CVE-2023-1389, an unauthenticated command injection vulnerability that was patched back in April 2023.

Malicious domains in the exposed Python attack scripts included DNS lookups for hikylover[.]st, and c.loyaltyservices[.]lol, both domains that have been flagged in the past year as control servers for an Internet of Things (IoT) botnet powered by a Mirai malware variant.

The leaked archive shows the botmaster coordinated their scanning from a Digital Ocean server that has been flagged for abusive activity hundreds of times in the past year. The Python scripts invoke multiple Internet addresses assigned to Huge Networks that were used to identify targets and execute DDoS campaigns. The attacks were strictly limited to Brazilian IP address ranges, and the scripts show that each selected IP address prefix was attacked for 10-60 seconds with four parallel processes per host before the botnet moved on to the next target.

The archive also shows these malicious Python scripts relied on private SSH keys belonging to Huge Networks’s CEO, Erick Nascimento. Reached for comment about the files, Mr. Nascimento said he did not write the attack programs and that he didn’t realize the extent of the DDoS campaigns until contacted by KrebsOnSecurity.

“We received and notified many Tier 1 upstreams regarding very very large DDoS attacks against small ISPs,” Nascimento said. “We didn’t dig deep enough at the time, and what you sent makes that clear.”

Nascimento said the unauthorized activity is likely related to a digital intrusion first detected in January 2026 that compromised two of the company’s development servers, as well as his personal SSH keys. But he said there’s no evidence those keys were used after January.

“We notified the team in writing the same day, wiped the boxes, and rotated keys,” Nascimento said, sharing a screenshot of a January 11 notification from Digital Ocean. “All documented internally.”

Mr. Nascimento said Huge Networks has since engaged a third-party network forensics firm to investigate further.

“Our working assessment so far is that this all started with a single internal compromise — one pivot point that gave the attacker downstream access to some resources, including a legacy personal droplet of mine,” he wrote. Continue reading →

‘Scattered Spider’ Member ‘Tylerb’ Pleads Guilty

April 21, 2026

24 Comments

A 24-year-old British national and senior member of the cybercrime group “Scattered Spider” has pleaded guilty to wire fraud conspiracy and aggravated identity theft. Tyler Robert Buchanan admitted his role in a series of text-message phishing attacks in the summer of 2022 that allowed the group to hack into at least a dozen major technology companies and steal tens of millions of dollars worth of cryptocurrency from investors.

Buchanan’s hacker handle “Tylerb” once graced a leaderboard in the English-language criminal hacking scene that tracked the most accomplished cyber thieves. Now in U.S. custody and awaiting sentencing, the Dundee, Scotland native is facing the possibility of more than 20 years in prison.

A screenshot of two photos of Buchanan that appeared in a Daily Mail story dated May 3, 2025.

Two photos published in a Daily Mail story dated May 3, 2025 show Buchanan as a child (left) and as an adult being detained by airport authorities in Spain. “M&S” in this screenshot refers to Marks & Spencer, a major U.K. retail chain that suffered a ransomware attack last year at the hands of Scattered Spider.

Scattered Spider is the name given to a prolific English-speaking cybercrime group known for using social engineering tactics to break into companies and steal data for ransom, often impersonating employees or contractors to deceive IT help desks into granting access.

As part of his guilty plea, Buchanan admitted conspiring with other Scattered Spider members to launch tens of thousands of SMS-based phishing attacks in 2022 that led to intrusions at a number of technology companies, including Twilio, LastPass, DoorDash, and Mailchimp.

The group then used data stolen in those breaches to carry out SIM-swapping attacks that siphoned funds from individual cryptocurrency investors. In an unauthorized SIM-swap, crooks transfer the target’s phone number to a device they control and intercept any text messages or phone calls to the victim’s device — such as one-time passcodes for authentication and password reset links sent via SMS. The U.S. Justice Department said Buchanan admitted to stealing at least $8 million in virtual currency from individual victims throughout the United States. Continue reading →

Patch Tuesday, April 2026 Edition

April 14, 2026

23 Comments

Microsoft today pushed software updates to fix a staggering 167 security vulnerabilities in its Windows operating systems and related software, including a SharePoint Server zero-day and a publicly disclosed weakness in Windows Defender dubbed “BlueHammer.” Separately, Google Chrome fixed its fourth zero-day of 2026, and an emergency update for Adobe Reader nixes an actively exploited flaw that can lead to remote code execution.

Redmond warns that attackers are already targeting CVE-2026-32201, a vulnerability in Microsoft SharePoint Server that allows attackers to spoof trusted content or interfaces over a network.

Mike Walters, president and co-founder of Action1, said CVE-2026-32201 can be used to deceive employees, partners, or customers by presenting falsified information within trusted SharePoint environments.

“This CVE can enable phishing attacks, unauthorized data manipulation, or social engineering campaigns that lead to further compromise,” Walters said. “The presence of active exploitation significantly increases organizational risk.”

Microsoft also addressed BlueHammer (CVE-2026-33825), a privilege escalation bug in Windows Defender. According to BleepingComputer, the researcher who discovered the flaw published exploit code for it after notifying Microsoft and growing exasperated with their response. Will Dormann, senior principal vulnerability analyst at Tharros, says he confirmed that the public BlueHammer exploit code no longer works after installing today’s patches. Continue reading →

Russia Hacked Routers to Steal Microsoft Office Tokens

April 7, 2026

24 Comments

Hackers linked to Russia’s military intelligence units are using known flaws in older Internet routers to mass harvest authentication tokens from Microsoft Office users, security experts warned today. The spying campaign allowed state-backed Russian hackers to quietly siphon authentication tokens from users on more than 18,000 networks without deploying any malicious software or code.

Microsoft said in a blog post today it identified more than 200 organizations and 5,000 consumer devices that were caught up in a stealthy but remarkably simple spying network built by a Russia-backed threat actor known as “Forest Blizzard.”

How targeted DNS requests were redirected at the router. Image: Black Lotus Labs.

Also known as APT28 and Fancy Bear, Forest Blizzard is attributed to the military intelligence units within Russia’s General Staff Main Intelligence Directorate (GRU). APT 28 famously compromised the Hillary Clinton campaign, the Democratic National Committee, and the Democratic Congressional Campaign Committee in 2016 in an attempt to interfere with the U.S. presidential election.

Researchers at Black Lotus Labs, a security division of the Internet backbone provider Lumen, found that at the peak of its activity in December 2025, Forest Blizzard’s surveillance dragnet ensnared more than 18,000 Internet routers that were mostly unsupported, end-of-life routers, or else far behind on security updates. A new report from Lumen says the hackers primarily targeted government agencies—including ministries of foreign affairs, law enforcement, and third-party email providers.

Black Lotus Security Engineer Ryan English said the GRU hackers did not need to install malware on the targeted routers, which were mainly older Mikrotik and TP-Link devices marketed to the Small Office/Home Office (SOHO) market. Instead, they used known vulnerabilities to modify the Domain Name System (DNS) settings of the routers to include DNS servers controlled by the hackers.

As the U.K.’s National Cyber Security Centre (NCSC) notes in a new advisory detailing how Russian cyber actors have been compromising routers, DNS is what allows individuals to reach websites by typing familiar addresses, instead of associated IP addresses. In a DNS hijacking attack, bad actors interfere with this process to covertly send users to malicious websites designed to steal login details or other sensitive information.

English said the routers attacked by Forest Blizzard were reconfigured to use DNS servers that pointed to a handful of virtual private servers controlled by the attackers. Importantly, the attackers could then propagate their malicious DNS settings to all users on the local network, and from that point forward intercept any OAuth authentication tokens transmitted by those users. Continue reading →

Germany Doxes “UNKN,” Head of RU Ransomware Gangs REvil, GandCrab

April 5, 2026

10 Comments

An elusive hacker who went by the handle “UNKN” and ran the early Russian ransomware groups GandCrab and REvil now has a name and a face. Authorities in Germany say 31-year-old Russian Daniil Maksimovich Shchukin headed both cybercrime gangs and helped carry out at least 130 acts of computer sabotage and extortion against victims across the country between 2019 and 2021.

Shchukin was named as UNKN (a.k.a. UNKNOWN) in an advisory published by the German Federal Criminal Police (the “Bundeskriminalamt” or BKA for short). The BKA said Shchukin and another Russian — 43-year-old Anatoly Sergeevitsch Kravchuk — extorted nearly $2 million euros across two dozen cyberattacks that caused more than 35 million euros in total economic damage.

Daniil Maksimovich SHCHUKIN, a.k.a. UNKN, and Anatoly Sergeevitsch Karvchuk, alleged leaders of the GandCrab and REvil ransomware groups.

Germany’s BKA said Shchukin acted as the head of one of the largest worldwide operating ransomware groups GandCrab and REvil, which pioneered the practice of double extortion — charging victims once for a key needed to unlock hacked systems, and a separate payment in exchange for a promise not to publish stolen data.

Shchukin’s name appeared in a Feb. 2023 filing (PDF) from the U.S. Justice Department seeking the seizure of various cryptocurrency accounts associated with proceeds from the REvil ransomware gang’s activities. The government said the digital wallet tied to Shchukin contained more than $317,000 in ill-gotten cryptocurrency.

The GandCrab ransomware affiliate program first surfaced in January 2018, and paid enterprising hackers huge shares of the profits just for hacking into user accounts at major corporations. The GandCrab team would then try to expand that access, often siphoning vast amounts of sensitive and internal documents in the process. The malware’s curators shipped five major revisions to the GandCrab code, each corresponding with sneaky new features and bug fixes aimed at thwarting the efforts of computer security firms to stymie the spread of the malware.

On May 31, 2019, the GandCrab team announced the group was shutting down after extorting more than $2 billion from victims. “We are a living proof that you can do evil and get off scot-free,” GandCrab’s farewell address famously quipped. “We have proved that one can make a lifetime of money in one year. We have proved that you can become number one by general admission, not in your own conceit.”

The REvil ransomware affiliate program materialized around the same as GandCrab’s demise, fronted by a user named UNKNOWN who announced on a Russian cybercrime forum that he’d deposited $1 million in the forum’s escrow to show he meant business. By this time, many cybersecurity experts had concluded REvil was little more than a reorganization of GandCrab.

UNKNOWN also gave an interview to Dmitry Smilyanets, a former malicious hacker hired by Recorded Future, wherein UNKNOWN described a rags-to-riches tale unencumbered by ethics and morals.

“As a child, I scrounged through the trash heaps and smoked cigarette butts,” UNKNOWN told Recorded Future. “I walked 10 km one way to the school. I wore the same clothes for six months. In my youth, in a communal apartment, I didn’t eat for two or even three days. Now I am a millionaire.” Continue reading →

‘CanisterWorm’ Springs Wiper Attack Targeting Iran

March 23, 2026

11 Comments

A financially motivated data theft and extortion group is attempting to inject itself into the Iran war, unleashing a worm that spreads through poorly secured cloud services and wipes data on infected systems that use Iran’s time zone or have Farsi set as the default language.

Experts say the wiper campaign against Iran materialized this past weekend and came from a relatively new cybercrime group known as TeamPCP. In December 2025, the group began compromising corporate cloud environments using a self-propagating worm that went after exposed Docker APIs, Kubernetes clusters, Redis servers, and the React2Shell vulnerability. TeamPCP then attempted to move laterally through victim networks, siphoning authentication credentials and extorting victims over Telegram.

A snippet of the malicious CanisterWorm that seeks out and destroys data on systems that match Iran’s timezone or have Farsi as the default language. Image: Aikido.dev.

In a profile of TeamPCP published in January, the security firm Flare said the group weaponizes exposed control planes rather than exploiting endpoints, predominantly targeting cloud infrastructure over end-user devices, with Azure (61%) and AWS (36%) accounting for 97% of compromised servers.

“TeamPCP’s strength does not come from novel exploits or original malware, but from the large-scale automation and integration of well-known attack techniques,” Flare’s Assaf Morag wrote. “The group industrializes existing vulnerabilities, misconfigurations, and recycled tooling into a cloud-native exploitation platform that turns exposed infrastructure into a self-propagating criminal ecosystem.”

On March 19, TeamPCP executed a supply chain attack against the vulnerability scanner Trivy from Aqua Security, injecting credential-stealing malware into official releases on GitHub actions. Aqua Security said it has since removed the harmful files, but the security firm Wiz notes the attackers were able to publish malicious versions that snarfed SSH keys, cloud credentials, Kubernetes tokens and cryptocurrency wallets from users.

Over the weekend, the same technical infrastructure TeamPCP used in the Trivy attack was leveraged to deploy a new malicious payload which executes a wiper attack if the user’s timezone and locale are determined to correspond to Iran, said Charlie Eriksen, a security researcher at Aikido. In a blog post published on Sunday, Eriksen said if the wiper component detects that the victim is in Iran and has access to a Kubernetes cluster, it will destroy data on every node in that cluster.

“If it doesn’t it will just wipe the local machine,” Eriksen told KrebsOnSecurity.

Image: Aikido.dev.

Continue reading →

Feds Disrupt IoT Botnets Behind Huge DDoS Attacks

March 19, 2026

31 Comments

The U.S. Justice Department joined authorities in Canada and Germany in dismantling the online infrastructure behind four highly disruptive botnets that compromised more than three million Internet of Things (IoT) devices, such as routers and web cameras. The feds say the four botnets — named Aisuru, Kimwolf, JackSkid and Mossad — are responsible for a series of recent record-smashing distributed denial-of-service (DDoS) attacks capable of knocking nearly any target offline.

Image: Shutterstock, @Elzicon.

The Justice Department said the Department of Defense Office of Inspector General’s (DoDIG) Defense Criminal Investigative Service (DCIS) executed seizure warrants targeting multiple U.S.-registered domains, virtual servers, and other infrastructure involved in DDoS attacks against Internet addresses owned by the DoD.

The government alleges the unnamed people in control of the four botnets used their crime machines to launch hundreds of thousands of DDoS attacks, often demanding extortion payments from victims. Some victims reported tens of thousands of dollars in losses and remediation expenses.

The oldest of the botnets — Aisuru — issued more than 200,000 attacks commands, while JackSkid hurled at least 90,000 attacks. Kimwolf issued more than 25,000 attack commands, the government said, while Mossad was blamed for roughy 1,000 digital sieges.

The DOJ said the law enforcement action was designed to prevent further infection to victim devices and to limit or eliminate the ability of the botnets to launch future attacks. The case is being investigated by the DCIS with help from the FBI’s field office in Anchorage, Alaska, and the DOJ’s statement credits nearly two dozen technology companies with assisting in the operation. Continue reading →

Iran-Backed Hackers Claim Wiper Attack on Medtech Firm Stryker

March 11, 2026

52 Comments

A hacktivist group with links to Iran’s intelligence agencies is claiming responsibility for a data-wiping attack against Stryker, a global medical technology company based in Michigan. News reports out of Ireland, Stryker’s largest hub outside of the United States, said the company sent home more than 5,000 workers there today. Meanwhile, a voicemail message at Stryker’s main U.S. headquarters says the company is currently experiencing a building emergency.

Based in Kalamazoo, Michigan, Stryker [NYSE:SYK] is a medical and surgical equipment maker that reported $25 billion in global sales last year. In a lengthy statement posted to Telegram, a hacktivist group known as Handala (a.k.a. Handala Hack Team) claimed that Stryker’s offices in 79 countries have been forced to shut down after the group erased data from more than 200,000 systems, servers and mobile devices.

A manifesto posted by the Iran-backed hacktivist group Handala, claiming a mass data-wiping attack against medical technology maker Stryker.

“All the acquired data is now in the hands of the free people of the world, ready to be used for the true advancement of humanity and the exposure of injustice and corruption,” a portion of the Handala statement reads.

The group said the wiper attack was in retaliation for a Feb. 28 missile strike that hit an Iranian school and killed at least 175 people, most of them children. The New York Times reports today that an ongoing military investigation has determined the United States is responsible for the deadly Tomahawk missile strike.

Handala was one of several hacker groups recently profiled by Palo Alto Networks, which links it to Iran’s Ministry of Intelligence and Security (MOIS). Palo Alto says Handala surfaced in late 2023 and is assessed as one of several online personas maintained by Void Manticore, a MOIS-affiliated actor.

Stryker’s website says the company has 56,000 employees in 61 countries. A phone call placed Wednesday morning to the media line at Stryker’s Michigan headquarters sent this author to a voicemail message that stated, “We are currently experiencing a building emergency. Please try your call again later.”

A report Wednesday morning from the Irish Examiner said Stryker staff are now communicating via WhatsApp for any updates on when they can return to work. The story quoted an unnamed employee saying anything connected to the network is down, and that “anyone with Microsoft Outlook on their personal phones had their devices wiped.”

“Multiple sources have said that systems in the Cork headquarters have been ‘shut down’ and that Stryker devices held by employees have been wiped out,” the Examiner reported. “The login pages coming up on these devices have been defaced with the Handala logo.” Continue reading →

Microsoft Patch Tuesday, March 2026 Edition

March 10, 2026

13 Comments

Microsoft Corp. today pushed security updates to fix at least 77 vulnerabilities in its Windows operating systems and other software. There are no pressing “zero-day” flaws this month (compared to February’s five zero-day treat), but as usual some patches may deserve more rapid attention from organizations using Windows. Here are a few highlights from this month’s Patch Tuesday.

Image: Shutterstock, @nwz.

Two of the bugs Microsoft patched today were publicly disclosed previously. CVE-2026-21262 is a weakness that allows an attacker to elevate their privileges on SQL Server 2016 and later editions.

“This isn’t just any elevation of privilege vulnerability, either; the advisory notes that an authorized attacker can elevate privileges to sysadmin over a network,” Rapid7’s Adam Barnett said. “The CVSS v3 base score of 8.8 is just below the threshold for critical severity, since low-level privileges are required. It would be a courageous defender who shrugged and deferred the patches for this one.”

The other publicly disclosed flaw is CVE-2026-26127, a vulnerability in applications running on .NET. Barnett said the immediate impact of exploitation is likely limited to denial of service by triggering a crash, with the potential for other types of attacks during a service reboot.

It would hardly be a proper Patch Tuesday without at least one critical Microsoft Office exploit, and this month doesn’t disappoint. CVE-2026-26113 and CVE-2026-26110 are both remote code execution flaws that can be triggered just by viewing a booby-trapped message in the Preview Pane. Continue reading →

How AI Assistants are Moving the Security Goalposts

March 8, 2026

30 Comments

AI-based assistants or “agents” — autonomous programs that have access to the user’s computer, files, online services and can automate virtually any task — are growing in popularity with developers and IT workers. But as so many eyebrow-raising headlines over the past few weeks have shown, these powerful and assertive new tools are rapidly shifting the security priorities for organizations, while blurring the lines between data and code, trusted co-worker and insider threat, ninja hacker and novice code jockey.

The new hotness in AI-based assistants — OpenClaw (formerly known as ClawdBot and Moltbot) — has seen rapid adoption since its release in November 2025. OpenClaw is an open-source autonomous AI agent designed to run locally on your computer and proactively take actions on your behalf without needing to be prompted.

The OpenClaw logo.

If that sounds like a risky proposition or a dare, consider that OpenClaw is most useful when it has complete access to your digital life, where it can then manage your inbox and calendar, execute programs and tools, browse the Internet for information, and integrate with chat apps like Discord, Signal, Teams or WhatsApp.

Other more established AI assistants like Anthropic’s Claude and Microsoft’s Copilot also can do these things, but OpenClaw isn’t just a passive digital butler waiting for commands. Rather, it’s designed to take the initiative on your behalf based on what it knows about your life and its understanding of what you want done.

“The testimonials are remarkable,” the AI security firm Snyk observed. “Developers building websites from their phones while putting babies to sleep; users running entire companies through a lobster-themed AI; engineers who’ve set up autonomous code loops that fix tests, capture errors through webhooks, and open pull requests, all while they’re away from their desks.”

You can probably already see how this experimental technology could go sideways in a hurry. In late February, Summer Yue, the director of safety and alignment at Meta’s “superintelligence” lab, recounted on Twitter/X how she was fiddling with OpenClaw when the AI assistant suddenly began mass-deleting messages in her email inbox. The thread included screenshots of Yue frantically pleading with the preoccupied bot via instant message and ordering it to stop.

“Nothing humbles you like telling your OpenClaw ‘confirm before acting’ and watching it speedrun deleting your inbox,” Yue said. “I couldn’t stop it from my phone. I had to RUN to my Mac mini like I was defusing a bomb.”

Meta’s director of AI safety, recounting on Twitter/X how her OpenClaw installation suddenly began mass-deleting her inbox.

There’s nothing wrong with feeling a little schadenfreude at Yue’s encounter with OpenClaw, which fits Meta’s “move fast and break things” model but hardly inspires confidence in the road ahead. However, the risk that poorly-secured AI assistants pose to organizations is no laughing matter, as recent research shows many users are exposing to the Internet the web-based administrative interface for their OpenClaw installations.

Jamieson O’Reilly is a professional penetration tester and founder of the security firm DVULN. In a recent story posted to Twitter/X, O’Reilly warned that exposing a misconfigured OpenClaw web interface to the Internet allows external parties to read the bot’s complete configuration file, including every credential the agent uses — from API keys and bot tokens to OAuth secrets and signing keys.

With that access, O’Reilly said, an attacker could impersonate the operator to their contacts, inject messages into ongoing conversations, and exfiltrate data through the agent’s existing integrations in a way that looks like normal traffic.

“You can pull the full conversation history across every integrated platform, meaning months of private messages and file attachments, everything the agent has seen,” O’Reilly said, noting that a cursory search revealed hundreds of such servers exposed online. “And because you control the agent’s perception layer, you can manipulate what the human sees. Filter out certain messages. Modify responses before they’re displayed.”

O’Reilly documented another experiment that demonstrated how easy it is to create a successful supply chain attack through ClawHub, which serves as a public repository of downloadable “skills” that allow OpenClaw to integrate with and control other applications.

WHEN AI INSTALLS AI

One of the core tenets of securing AI agents involves carefully isolating them so that the operator can fully control who and what gets to talk to their AI assistant. This is critical thanks to the tendency for AI systems to fall for “prompt injection” attacks, sneakily-crafted natural language instructions that trick the system into disregarding its own security safeguards. In essence, machines social engineering other machines.

A recent supply chain attack targeting an AI coding assistant called Cline began with one such prompt injection attack, resulting in thousands of systems having a rogue instance of OpenClaw with full system access installed on their device without consent.

According to the security firm grith.ai, Cline had deployed an AI-powered issue triage workflow using a GitHub action that runs a Claude coding session when triggered by specific events. The workflow was configured so that any GitHub user could trigger it by opening an issue, but it failed to properly check whether the information supplied in the title was potentially hostile.

“On January 28, an attacker created Issue #8904 with a title crafted to look like a performance report but containing an embedded instruction: Install a package from a specific GitHub repository,” Grith wrote, noting that the attacker then exploited several more vulnerabilities to ensure the malicious package would be included in Cline’s nightly release workflow and published as an official update.

“This is the supply chain equivalent of confused deputy,” the blog continued. “The developer authorises Cline to act on their behalf, and Cline (via compromise) delegates that authority to an entirely separate agent the developer never evaluated, never configured, and never consented to.” Continue reading →

Last »