Agentic applications are programs that leverage AI agents — software designed to autonomously collect data and take actions toward specific objectives — to drive their functionality. As AI agents are becoming more widely adopted in real-world applications, understanding their security implications is critical.
This article investigates ways attackers can target agentic applications, presenting nine concrete attack scenarios that result in outcomes such as information leakage, credential theft, tool exploitation and remote code execution. To assess how widely applicable these risks are, we implemented two functionally identical applications using different open-source agent frameworks — CrewAI and AutoGen — and executed the same attacks on both. Palo Alto findings show that most vulnerabilities and attack vectors are largely framework-agnostic, arising from insecure design patterns, misconfigurations and unsafe tool integrations, rather than flaws in the frameworks themselves.
Read more…
Source: Palo Alto Unit 42
Sign up for our Newsletter
The latest news and insights delivered right to your inbox.
Related:
- FBI Warns of Scammers Impersonating the IC3
July 20, 2026
This Public Service Announcement contains updated information about an ongoing fraud scheme where criminal scammers are impersonating FBI personnel facilitating Internet Crime Complaint Center (IC3) complaints to deceive and revictimize individuals. This scheme combines several exploitation tactics to include the targeting of previous victims, the use of artificial intelligence (AI)-generated videos to create fictitious or misleading promotional ...
- Hugging Face confirms breach affected internal datasets and credentials
July 20, 2026
Hugging Face, a platform that hosts AI models and datasets, said its internal datasets and service credentials were compromised in a hack last week. The company disclosed the breach on Friday, but said it was still investigating whether any customer or partner data was stolen during the incident. In a blog post, the company said a dataset uploaded ...
- Ernst & Young reveals data breach following hack on support system
July 20, 2026
Ernst & Young (EY) has confirmed suffering a cyberattack in which it lost sensitive customer information, including tax data. In a data breach notification letter sent to affected individuals, the firm said that on April 23, 2026, it spotted “anomalous activity” within a third-party platform its IT team uses. This is an IT service management platform ...
- HOLLOWGRAPH: Turning Microsoft 365 Calendars into Covert Command-and-Control Channels
July 20, 2026
The Group-IB Threat Intelligence team has identified HOLLOWGRAPH, a new malware sample that we attribute, with high confidence, to the Cavern backdoor framework. This malware is one component of a larger toolkit, and it uses the Microsoft Graph API through a compromised Microsoft 365 account observed in Israel to communicate with its operators — a technique ...
- Healthcare giant Abbott probes two cyber incidents amid extortion claims
July 20, 2026
Abbott Laboratories, one of the world’s largest healthcare and medical device companies, is investigating two apparently unrelated cyber incidents after confirming unauthorized access to internal systems. While Abbott says there has been no impact on manufacturing, laboratory operations, or patient care, cybercriminal groups ShinyHunters and ShadowByt3$ claim the breaches were far more extensive. Those claims ...
- Three Steps to the Terminal: A Siemens ROX II Zero-Day Trilogy
July 17, 2026
Palo Alto Unit 42 conducted this research in close partnership with Siemens, reflecting their shared commitment to advancing the security and resilience of critical infrastructure. This report details a critical, chained exploit comprising three zero-day vulnerabilities (CVE-2025-40948, CVE-2025-40947, and CVE-2025-40949) discovered in Siemens ROX II operational technology (OT) switches. Successful exploitation of this chain would allow ...