Large language models (LLMs) and AI agents are becoming deeply integrated into web browsers, search engines and automated content-processing pipelines. While these integrations can expand functionality, they also introduce a new and largely underexplored attack surface.
One particularly concerning class of threats is indirect prompt injection (IDPI), in which adversaries embed hidden or manipulated instructions within website content that is later ingested by an LLM. This article shares in-the-wild observations from our telemetry, including our first observed case of AI-based ad review evasion.
Read more…
Source: Palo Alto Unit 42
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Midnight Blizzard targets travelers worldwide for malware delivery and credential theft
July 31, 2026
Since early May 2026, Microsoft Threat Intelligence has observed Storm-2945, a sub-cluster of Midnight Blizzard, conducting widespread but targeted traffic manipulation attacks involving hospitality sector networks served by captive portals worldwide. Despite some tactic, technique, and procedure (TTP) similarities to the Forest Blizzard DNS hijacking operation that we publicly disclosed in April 2026, we attribute this campaign, ...
- Network Anomaly Detection in KATA
July 31, 2026
Once the attacker has breached the corporate network, subsequent stages of the attack often involve leveraging standard domain infrastructure protocols: using Kerberos, running DNS queries, accessing internal services, opening network shares, and other common networking actions. Because this activity is virtually indistinguishable from legitimate network traffic, it is extremely difficult to detect it with traditional ...
- Toy Ghouls’ new toy: the GenieLocker ransomware
July 30, 2026
The new GenieLocker ransomware family has been active since March 2026. It has been used in attacks against organizations in the Russian Federation, primarily in the manufacturing sector, and attributed to the Toy Ghouls group by open-source intelligence (link in Russian). The Toy Ghouls, also known as Bearlyfy, Labubu and Laboo.boo, is a financially motivated extortion group, which ...
- Durov’s bank accounts frozen after terrorist tag applied
July 30, 2026
Telegram co-founder Pavel Durov will not be able to access his bank accounts in Russia after placement on the list of terrorists by financial watchdog Rosfinmonitoring earlier on Thursday, lawyer Dmitry Agranovsky told TASS. Since 2022, Russia has recorded 153,000 crimes committed using Telegram, including the organization of a terrorist attack at the Crocus City Hall, ...
- OpenAI explains how its AI agent breached Hugging Face
July 29, 2026
On July 28, OpenAI published an update on the agent that escaped its sandbox and hacked into Hugging Face during an internal cybersecurity evaluation. In the update, OpenAI reiterates that the “rogue” system was a more capable, pre‑release research model, not something intended for public deployment, and that it has now been deactivated and locked down for restricted research ...
- Check Point SmartConsole Authentication Bypass Technical Analysis (CVE-2026-16232)
July 29, 2026
On July 22, 2026, Check Point published a security advisory for CVE-2026-16232, an authentication bypass in the SmartConsole login process affecting Security Management Server and Multi-Domain Security Management Server (MDS). By leveraging CVE-2026-16232, an unauthenticated attacker can obtain an application login token, use this token to log in through SmartConsole with full administrator privileges, and modify the security policy ...