Skip to content Skip to sidebar Skip to footer

How to Secure AI Agents as Attackers Use AI to Scale Cyber Operations

What Happened Microsoft assesses North Korean threat actors’ AI adoption as high, while describing their operations as human-directed. Reported uses include faster reconnaissance, fraudulent job applications, targeted social engineering and malware development. Microsoft also reports use of an agentic penetration-testing framework by two groups and possible AI-generated voice and video use by another [2]. Microsoft…

Read More

How to Secure AI Agents Without Expanding Your Attack Surface

What Happened Microsoft Security reports that active agents in its Microsoft 365 ecosystem grew 15-fold year over year, and 18-fold in large enterprises. It frames the CISO’s task as both governing those agents and defending against AI-enabled attacks [2]. Separately, Unit 42 highlights ransomware and AI-enabled attacks among the threats retailers face during peak shopping…

Read More

How a Compromised AI Dependency Can Steal Credentials Before Your Application Starts

What Happened A compromised LiteLLM 1.107.0 release reached PyPI and official container images on October 21, 2026. Maintainers said stolen developer GitHub credentials redirected the release workflow to a lookalike repository; how those credentials were obtained has not been independently established. [1] The wheel installed Python startup files named cook.pth, cook.py, and sitecustomize.py. These could…

Read More

Critical PHP Vulnerabilities: How to Protect AI Applications That Depend on Web Infrastructure

What Happened Unit 42 identified CVE-2026-109618 and CVE-2026-109619 as critical PHP vulnerabilities in a threat brief updated October 23. PHP is widely used in web servers and content management systems. The available brief does not establish the affected versions, exploit conditions, or whether attacks have occurred [1]. Why It Matters to Businesses An AI application…

Read More

How to Contain AI-Accelerated Attacks Across Vendor Access, OAuth and TLS Trust

What Happened Microsoft assesses that Storm-0940, a China-state-aligned actor, used the ARTEX AI penetration-testing framework to accelerate attacks and was responsible for a ConnectWise Cloud Backup supply-chain compromise. In one October 10–14 campaign, Microsoft observed more than 151,000 failed logons against 327 accounts at eight organizations, with no successful authentication in that campaign. Following the…

Read More

How AI-Accelerated Attacks Change Cloud Defense and Secure Code Review

What Happened Microsoft attributes a campaign targeting hundreds of organizations to China-state-aligned Storm-0940. Microsoft says the actor used the agentic penetration-testing framework ARTEX to accelerate scanning, password spraying and OAuth application abuse, and assesses that the actor was responsible for a disclosed ConnectWise supply-chain compromise. Some attacks reached privileged cloud access in under three hours.…

Read More

How to Secure AI Agents Without Losing Sight of Active Infrastructure Threats

What Happened Unit 42 reports that ransomware operators, including Spikey Scorpius (Qilin) and Tarnished Scorpius (Inc), are actively exploiting PAN-OS CVE-2026-0257. Its updated threat brief establishes active exploitation, but the research notes do not specify the exploit mechanism or affected configurations [1]. Microsoft Security argues that AI agents create a different kind of exposure: they…

Read More

How to Secure AI Agents Without Overlooking Exploited Network Vulnerabilities

What Happened Unit 42 reports active ransomware exploitation of PAN-OS CVE-2026-0257, including activity attributed to Spikey Scorpius (Qilin) and Tarnished Scorpius (Inc). Its threat brief was updated on October 19 [1]. Microsoft describes AI agents as a new insider-risk category: agents can act across business systems at machine speed, whether their actions result from mistakes,…

Read More

How to Secure Enterprise AI Applications Beyond Model Evaluations

What Happened Recent security reporting highlights two connected problems for AI deployments. Unit 42 identified edge exploits, credential abuse and phishing among the leading initial-access vectors it observed in September 2026; the available summary does not name the remaining two vectors [1]. Separately, Microsoft and NVIDIA published enterprise guidance arguing that open-weight model risk depends…

Read More

How to Defend Government Linux Infrastructure Against AI-Enabled Espionage

What Happened Unit 42 reported an AI-powered espionage campaign targeting government Linux infrastructure. Its report describes custom malware, web shells, and advanced credential theft. The available account does not identify the attackers, affected governments, campaign dates, or exactly how AI was used [1]. Why It Matters to Businesses The reported techniques are not limited to…

Read More

How to Secure AI Applications Against Phishing, Firewall Implants and Package Tampering

What Happened Three investigations show how attackers can reach the infrastructure around an AI application without attacking the model itself. Unit 42 investigated an intrusion involving exploitation of CVE-2024-47575, targeting more than 500 FortiGate firewalls and deploying PEERSTITCH, a memory-resident ARM64 implant [1]. Microsoft and Resecurity identified a phishing ecosystem whose kits have been used…

Read More

How a Basic Bank Attack Exposed Third-Party Risk—and What AI Teams Should Secure Next

What Happened Unit 42 examined an unsophisticated attack against a European bank’s IT infrastructure that exposed a third-party risk within the bank’s network. The available account does not specify the attack path, the third party’s role, or whether AI systems were involved. Unit 42 also discussed ways to detect and counter similar threats [1]. Why…

Read More

Engineering Founded & Customer Focused

KIMBODO LLC. © 2026. All Rights Reserved.