Model Context Protocol is a technology platform tracked across 8 threat clusters and 10 intelligence report mentions on ThreatCluster. First observed November 17, 2025; most recent activity June 5, 2026.
On June 4, 2026, Microsoft updated its 'Taxonomy of Failure Modes in Agentic AI Systems' based on a year of red teaming. The update highlights the emergence of zero-click attack chains that can bypass human-in-the-loop…
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…
Backslash Security has introduced cross-product support for AI Skills, enabling organizations to discover and govern the use of these Skills in AI-native development environments. Skills allow AI coding tools to perform…
On November 19, 2025, the United States, United Kingdom, and Australia announced coordinated sanctions against the Russian web company Media Land, accusing it of facilitating ransomware operations. The sanctions include…
A security flaw known as DockerDash has been identified in Docker's Ask Gordon AI assistant, allowing attackers to manipulate metadata and influence execution flow. This vulnerability affects the Model Context Protocol…
Kali Linux has introduced a new AI-assisted penetration testing workflow utilizing Anthropic’s Claude AI. This integration allows security professionals to issue natural-language commands that are converted into…
In 2026, the rise of agentic AI is transforming how businesses operate, particularly in the financial services sector. This new technology allows for autonomous decision-making, which increases the potential impact of…
Anthropic has addressed three vulnerabilities in its Git MCP server, which could be exploited to remotely execute malicious code or overwrite files through prompt injection. The server connects various AI tools to Git…