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:
- Cyber security: Nation-state cyber attacks threaten everyone, warns ex-GCHQ boss
June 8, 2018
The dynamics of cyber warfare have changed so dramatically that nation-state attacks are now a problem everyone needs to face up to, the former head of the UK’s intelligence agency has warned. “Five years ago we were aware of nation-state attacks but we would’ve seen them as something that only a nation-state needs to worry about. Today they’re ...
- Researchers Warn of Microsoft Zero-Day RCE Bug
June 1, 2018
Researchers have discovered a medium-severity Windows vulnerability that enables remote attackers to execute arbitrary code – and Microsoft hasn’t issued a patch yet. The flaw, which was first discovered by Dmitri Kaslov of Telspace Systems, exists within the handling of error objects in JScript, according to a Tuesday advisory by Trend Micro’s Zero Day Initiative group. Read more… Source: ...
- Microsoft, Google: We’ve found a fourth variant of Meltdown-Spectre CPU holes
May 21, 2018
A fourth variant of the data-leaking Meltdown-Spectre security flaws in modern processors has been found by Microsoft and Google researchers. These speculative-execution design blunders can be potentially exploited by malicious software running on a vulnerable device or computer, or a miscreant logged into the system, to slowly extract secrets, such as passwords, from protected kernel or application memory, ...
- One Year After WannaCry: A Fundamentally Changed Threat Landscape
May 17, 2018
It’s been one year this week since the ransomware known as WannaCry infected more than 200,000 machines in 150 countries, causing billions of dollars in damages and grinding global business to a halt. The speed and scale of the attack – helped along by leaked National Security Agency hacking tools – was obviously notable, but ...
- Critical Linux Flaw Opens the Door to Full Root Access
May 16, 2018
Red Hat has patched a vulnerability affecting the DHCP client packages that shipped with Red Hat Enterprise Linux 6 and 7. A successful exploit could give an attacker root access and full control over enterprise endpoints. According to an alert issued Wednesday from US-CERT, the critical-rated flaw, first reported by Google researcher Felix Wilhelm, would “allow attackers to ...
- Nethammer—Exploiting DRAM Rowhammer Bug Through Network Requests
May 16, 2018
Last week, we reported about the first network-based remote Rowhammer attack, dubbed Throwhammer, which involves the exploitation a known vulnerability in DRAM through network cards using remote direct memory access (RDMA) channels. However, a separate team of security researchers has now demonstrated a second network-based remote Rowhammer technique that can be used to attack systems using uncached memory or ...