CVE-2025-54136

CVE

Threat entity extracted from intelligence sources

Frequency

occurrences

First Seen

March 17, 2026

Last Seen

October 7, 2026

API

Exploited in Wild

—

Ransomware Use

—

Public Exploits

—

Attack Vector

—

Vulnerability Overview

Exploitation Activity

Exploitation Intelligence

AI Coding Agents Expand Software Supply Chain Risks71.8

AI coding agents are introducing significant vulnerabilities into the software supply chain by selecting insecure dependencies without human oversight. Research indicates that only 20% of dependency versions recommended by these agents are safe, leading to a surge in malicious packages. In 2025, ove...

Critical Command Injection Flaw in Progress DataDirect GenAI Agents70.5

Progress Software disclosed a critical command injection vulnerability, tracked as CVE-2026-91140, in its DataDirect Autonomous REST Connector GenAI Agents. This flaw allows attackers to execute arbitrary operating system commands via specially crafted OpenAPI or Swagger documents. The vulnerability...

CursorJack Vulnerability Exposes Code Execution Risks in AI Development Environments54.9

Proofpoint Threat Research has identified a vulnerability named CursorJack that exploits deeplinks in the Cursor Integrated Development Environment (IDE). This method allows attackers to potentially execute arbitrary code or install malicious components by manipulating Model Context Protocol (MCP) d...

Emergence of Agentic AI Raises Governance and Security Challenges35.2

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 errors and security breaches. IT leaders are actively addressing these challenges...