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:
- Ransomware: Is time running out for the biggest menace on the web?
January 26, 2018
Ransomware attacks like WannaCry and Petya caused major chaos last year, while the likes of Locky and Cerber were less high-profile, but still managed to generate large amounts of income for their criminal creators. 2017 was the year of ransomware, but it could be that the file-encrypting malware has already reached its peak, as an analysis of cybercriminal campaigns appears to show that malicious ...
- Satori Author Linked to New Mirai Variant Masuta
January 23, 2018
Researchers at NewSky Security say the hacker behind a Mirai malware variant called Satori, also known as Mirai Okiru, is the same hacker behind two new Mirai variants called Masuta and PureMasuta. Based on source code for Masuta malware recently found on the dark web, researchers at NewSky Security said they were able to connect the ...
- Triple Meltdown: How So Many Researchers Found A 20-Year-Old Chip Flaw At The Same Time.
January 7, 2018
On a cold Sunday early last month in the small Austrian city of Graz, three young researchers sat down in front of the computers in their homes and tried to break their most fundamental security protections. Two days earlier, in their lab at Graz’s University of Technology, Moritz Lipp, Daniel Gruss, and Michael Schwarz had determined to ...
- Kernel-memory-leaking Intel processor design flaw forces Linux, Windows redesign
January 2, 2018
A fundamental design flaw in Intel’s processor chips has forced a significant redesign of the Linux and Windows kernels to defang the chip-level security bug. Programmers are scrambling to overhaul the open-source Linux kernel’s virtual memory system. Meanwhile, Microsoft is expected to publicly introduce the necessary changes to its Windows operating system in an upcoming Patch ...
- MacOS LPE Exploit Gives Attackers Root Access
January 2, 2018
A researcher that goes by the handle “Siguza” released details of a local privilege escalation attack against macOS that dates back to 2002. A successful attack could give adversaries complete root access to targeted systems. Siguza released details of the attack on Dec. 31 via Twitter, wishing followers a “Happy New Year” and linked to a ...
- Triton Malware Targets Industrial Control Systems in Middle East
December 15, 2017
Researchers found malware called Triton on the industrial control systems of a company located in the Middle East. Attackers planted Triton, also called Trisis, with the intent of carrying out a “high-impact attack” against an unnamed company with the goal of causing physical damage, researchers said. FireEye’s Mandiant threat research team revealed the existence of the malware ...