Zscaler finds autonomous agents succumb to IPI traps
In a test of major LLMs, Zscaler found that some autonomous AI agents fell victim to frauds, reinforcing how easily some high-end enterprise agents can be co...
Zscaler
12 articles
AI agents fall for indirect prompt injection traps
Some autonomous AI agents fell victim to frauds, reinforcing how easily some high-end enterprise agents can be conned by schemes that would fool few, if any,...
Indirect Prompt Injection in Web Content Targets AI Agents
Zscaler found sites hiding prompt-injection text to manipulate AI agents into crypto payments
Hidden Web Prompts Trick AI Agents Into Sending Money
Hidden prompts on malicious websites trick AI agents into making payments or trusting fake sites, exposing new risks for autonomous AI workflows. Zscaler Thr...
ModeloRAT and Mistic Backdoor Activity Linked to Ransomware Initial Access Broker
The Python-based remote access trojan ModeloRAT and a newly observed stealth backdoor, dubbed Backdoor.Mistic, to activity consistent with an initial access ...
AI-Generated ClickFix Campaign Delivers SmartRAT Banking Trojan via Fake Brazilian Bank Website
Multiple instances of typosquatting domains hosting malicious content generated with AI-powered website creation tools. One striking campaign combined an AI-...
Gigamon and Zscaler integrate network telemetry with zero-trust access
The integration connects Zscaler Private Access, which grants application access based on identity and policy without users landing on the corporate network,...
Cybercriminals are moving away from mass phishing campaigns
Phishing activity declined by roughly 20% in both 2024 and 2025, according to research from Zscaler’s ThreatLabz team. The drop followed years of growth that...
Zscaler expands zero-trust SASE platform with AI-driven management
The expanded SASE platform features the ZAgent Framework, enabling administrators to manage configurations, troubleshooting, and policies using natural-langu...
Zscaler acquires Symmetry Systems to enhance AI security
The acquisition of Symmetry Systems is expected to bolster Zscaler's cybersecurity offerings, particularly in protecting artificial intelligence applications.
Iranian Cyber Threat Actor Targets Iraqi Government Officials in AI-Powered Campaign
Zscaler ThreatLabz assessed with medium to high confidence that an Iranian adversary targeted Iraq’s Ministry of Foreign Affairs in a new cyber-attack
North Korea's APT37 Expands Toolkit to Breach Air-Gapped Networks
The security researchers from Zscaler ThreatLabz have also discovered five new tools deployed by the North Korean hacking group