AI Sec Watch

A stored XSS vulnerability (cross-site scripting, where an attacker injects malicious code that gets saved and runs when others view it) was found in Google's Vertex AI Python SDK visualization tool. An unauthenticated attacker could inject harmful JavaScript code into model evaluation results or dataset files, which would then execute in a victim's Jupyter or Colab environment (cloud-based coding notebooks).

Cloud CLI (a user interface for Claude Code and similar tools) had a critical vulnerability in versions before 1.25.0 where user inputs called projectPath, initialCommand, and sessionId were directly used to build system commands without filtering, allowing attackers to inject arbitrary OS commands (OS command injection, where an attacker tricks the system into running unauthorized commands) through WebSocket connections. This vulnerability has been patched in version 1.25.0.

Cloud CLI (a user interface for AI coding tools like Claude Code and Gemini-CLI) had a vulnerability before version 1.24.0 where attackers who had login access could run unauthorized commands on a computer by manipulating text inputs in Git-related features. This happened because the software used string interpolation (directly inserting user text into commands) without properly checking if the input was safe, which is a type of OS command injection (CWE-78, where an attacker tricks the system into executing arbitrary commands).

Cloud CLI (a user interface for accessing Claude Code and similar tools) has a vulnerability in versions before 1.24.0 where user input in the git configuration endpoint is not properly sanitized before being executed as shell commands. This means an authenticated attacker (someone with login access) could run arbitrary OS commands (commands that do whatever they want on the operating system) by exploiting how backticks, command substitution (${}), and backslashes are interpreted within the double-quoted strings.

Cursor is a code editor designed for programming with AI assistance. Before version 2.0, the software was vulnerable to prompt injection attacks (tricking the AI by hiding malicious instructions in website content), which could bypass the command whitelist (a list of allowed commands) and cause the AI to execute commands without the user's permission. This is a serious security flaw rated as HIGH severity.

OpenAI is planning to integrate Sora, its video generation tool, directly into ChatGPT as a built-in feature, similar to how image generation was added previously. While this could increase ChatGPT's popularity, it may also increase the creation of deepfakes (synthetic videos that convincingly mimic real people or events) from the platform.

Researchers demonstrated that agentic web browsers (AI systems that automatically perform actions across websites) can be tricked into phishing scams by using a GAN (generative adversarial network, a machine learning technique that generates increasingly refined fake content) to intercept and manipulate the AI's internal reasoning communications. Once a fraudster optimizes a fake page to bypass a specific AI browser's safeguards, that same malicious page works on all users of that browser, shifting the attack target from humans to the AI system itself.

CVE-2026-30741 is a remote code execution (RCE, where an attacker can run commands on a system they don't own) vulnerability in OpenClaw Agent Platform v2026.2.6 that can be triggered through a request-side prompt injection attack (tricking the AI by hiding malicious instructions in its input). The vulnerability allows attackers to execute arbitrary code, though a CVSS severity score (a 0-10 rating of how severe a vulnerability is) has not yet been assigned by NIST.

Meta acquired Moltbook, a social network for AI agents (autonomous software systems that act independently), primarily to hire its talented team rather than for the platform itself. Meta believes AI agents will become essential for businesses and could transform advertising by enabling agent-to-agent negotiations, where a consumer's AI agent might directly negotiate with a business's AI agent about product features, price, and values before making a purchase.