Anthropic has fixed three bugs in its official Git MCP server that researchers say can be chained with other MCP tools to ...

PromptArmor, a security firm specializing in the discovery of AI vulnerabilities, reported on Wednesday that Cowork can be ...

Researchers found an indirect prompt injection flaw in Google Gemini that bypassed Calendar privacy controls and exposed ...

A calendar-based prompt injection technique exposes how generative AI systems can be manipulated through trusted enterprise ...

Three vulnerabilities in Anthropic’s MCP Git server allow prompt injection attacks that can read or delete files and, in some cases, lead to RCE.

Attackers are now exploiting a critical Fortinet FortiSIEM vulnerability with publicly available proof-of-concept exploit code.

PromptArmor threat researchers uncovered a vulnerability in Anthropic's new Cowork that already was detected in the AI company's Claude Code developer tool, and which allows a threat actor to trick ...

Exploit code has been published for CVE-2025-64155, a critical command injection vulnerability affecting Fortinet FortiSIEM ...

LLMs change the security model by blurring boundaries and introducing new risks. Here's why zero-trust AI is emerging as the ...

Technical details and a public exploit have been published for a critical vulnerability affecting Fortinet's Security ...

The phishing campaign shows how attackers continue to weaponize legitimate cloud services and open source tools to evade ...

Varonis found a “Reprompt” attack that let a single link hijack Microsoft Copilot Personal sessions and exfiltrate data; Microsoft patched it in January 2026.