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:
- Free Spotify Premium hacks on social media are spreading infostealers
June 10, 2026
Short-form video platforms like TikTok and Instagram Reels have become the latest way cybercriminals spread malware. We’ve already seen attackers move away from traditional phishing emails and toward tactics that trick people into installing malware themselves. Now they’re being lured with slick social media videos that promise free Spotify Premium, free Windows activation, or free Microsoft Office, but ...
- France probes compromise of gov messaging platform after account hijack
June 9, 2026
French officials are investigating a compromise of the government’s encrypted messaging service Tchap after attackers hijacked an account and gained access to public chat rooms. The incident came to light on June 7 when France’s National Cybersecurity Agency (ANSSI) detected suspicious activity on Tchap, the government’s homegrown messaging service used across ministries and public sector organizations. The French ...
- CISA gives US federal agencies three days to fix a VPN bug under attack by a ransomware gang
June 9, 2026
A ransomware group is actively exploiting an unpatched flaw in security tools used across the U.S. federal government, prompting the U.S. cybersecurity agency CISA to order all civilian agencies to remediate the vulnerability by end of day Wednesday. Cybersecurity firm Check Point Software said the bug affects several of its remote access tools, firewalls, and VPNs, which act as ...
- Chrome’s zero-day Whac-A-Mole continues with fifth exploited bug of the year
June 9, 2026
Google has fixed its fifth actively exploited Chrome zero-day of 2026, and this one earned its finder a $55,000 bounty. The flaw, tracked as CVE-2026-11645, is an out-of-bounds memory access bug in Chrome’s V8 JavaScript engine. Google confirmed that the vulnerability is being exploited in the wild, but has disclosed little beyond the bare technical details. Read ...
- WhatsApp says it caught new spyware attacks linked to NSO Group in violation of court order
June 8, 2026
WhatsApp said that it disrupted a new hacking campaign linked to NSO Group, a spyware maker that has been ensnared in countless cases of abuse all over the world. The messaging app maker accused NSO of violating an earlier court order that bars the company from targeting WhatsApp and its users with its spyware, and is seeking to ...
- Microsoft’s open source tools were hacked to steal passwords of AI developers
June 8, 2026
Microsoft has cut off access to dozens of its open source projects hosted on GitHub as it investigates how hackers apparently breached the projects and injected password-stealing malware into the code. Many of the affected projects relate to Microsoft’s cloud service Azure and other tools used by developers to code with AI development apps, such as ...