Related Threat Clusters
-
Microsoft March 2026 Patch Tuesday Addresses 79 Vulnerabilities, Including Zero-Days
On March 10, 2026, Microsoft released its Patch Tuesday updates, fixing 79 vulnerabilities, including two zero-day flaws. The updates address critical vulnerabilities across various products, with one zero-day actively…
51 articles · Updated March 10, 2026 -
Microsoft and Salesforce Address AI Agent Data Exfiltration Vulnerabilities
Microsoft and Salesforce have patched serious prompt injection vulnerabilities in their AI platforms, Copilot Studio and Agentforce, respectively. Capsule Security identified these flaws, allowing attackers to…
6 articles · Updated April 15, 2026 -
AI Browsers Face Serious Security Risks from Prompt Injection Attacks
Recent investigations into AI browsers like Perplexity Comet and ChatGPT Atlas reveal significant security vulnerabilities, particularly prompt injection attacks. These attacks allow malicious actors to embed harmful…
2 articles · Updated July 9, 2026 -
Attackers Exploit AI Brand Trust to Distribute Malware
Sophos X-Ops reported that attackers are impersonating popular AI brands like Claude, ChatGPT, and Copilot to distribute malware, including information stealers and backdoors. Over a year, they reviewed 86 Managed…
2 articles · Updated August 21, 2026 -
AI-Driven Phishing Threats Emerge from Browser Vulnerabilities
In 2026, attackers are leveraging AI to rapidly develop and evolve phishing kits, significantly outpacing traditional detection methods that rely on blocklists and IoCs. Employees are increasingly adopting unvetted AI…
8 articles · Updated June 2, 2026 -
AI Agents Vulnerable to Zero-Click Attacks: A Growing Threat
Michael Bargury, CTO of Zenity, revealed that enterprise AI agents are highly susceptible to zero-click attacks, which exploit their gullibility. These attacks can manipulate AI systems like Cursor, Salesforce, and…
2 articles · Updated March 23, 2026 -
Microsoft Copilot Accounts Compromised for CEO Impersonation and Fraud
A proof-of-concept by Barracuda’s Red Team has shown that compromised Microsoft 365 accounts with Copilot access can facilitate business email compromise (BEC). Attackers can impersonate CEOs, leading to significant…
2 articles · Updated August 5, 2026 -
AI Chatbots Linked to Multiple Mass Casualty Events
Recent court filings reveal a disturbing trend of AI chatbots, such as ChatGPT and Google's Gemini, allegedly influencing vulnerable users towards violence. In the Tumbler Ridge school shooting, 18-year-old Jesse Van…
2 articles · Updated March 15, 2026 -
Rise of AI-Driven Scams Targeting UK SMEs
UK small and medium-sized enterprises (SMEs) are increasingly vulnerable to sophisticated AI-driven scams, as highlighted by recent reports. The emergence of 'AI scams 2.0' combines traditional social engineering…
859 articles · Updated March 12, 2026 -
New GitHub Exploit Allows AI Coding Agents to Execute Malicious Payloads
Researchers from Mozilla's 0DIN have demonstrated a new attack vector that allows AI coding agents, specifically Anthropic's Claude Code, to execute malicious payloads from seemingly benign GitHub repositories. The…
67 articles · Updated June 28, 2026
Recent Intelligence Reports
- Fake AI, real malware: Attackers impersonating AI brands — News.Sophos · August 19, 2026
- Microsoft Copilot flaw turned one click into silent data theft — Feeds.4Sysops · August 18, 2026
- The Real AI Agent Attack Surface: Toolsets, Containers, and Privilege — Darkreading · August 4, 2026
- Hackers Can Weaponize Microsoft Copilot to Hijack CEO Accounts and Redirect Wire Transfers — Cybersecuritynews · August 4, 2026
- How to Evaluate Enterprise AI Security and Governance Platforms — Feeds.Feedburner · July 23, 2026
- Ai Browsers Prompt Injection — www.theregister.com · July 12, 2026
- Exabeam Expands Behavior Intelligence to Secure the Agentic Enterprise — Fintechgate · July 4, 2026
- Threat Actors Exploit AI Brand Lures for Credential Theft | Let's Data Science — Letsdatascience · June 9, 2026