Microsoft

When prompts become shells: RCE vulnerabilities in AI agent frameworks

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...
SDxCentral

VU#148244: PandasAI interactive prompt function can be exploited to run arbitrary Python code through prompt injection, which can lead to remote code execution (RCE)

PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...

US CISA adds ‘insane’ Linux Copy Fail flaw to watch list

Malicious actors with code execution capability may gain root access on Linux systems using as few as 10 lines of Python, according to a researcher.

YubiKey Manager: Security vulnerability allows execution of injected code

Yubico warns of a search path vulnerability in YubiKey Manager, libfido2 and python-fido2. Updates fix the bugs.
Bleeping Computer

WhatsApp for Windows lets Python, PHP scripts execute with no warning

A security issue in the latest version of WhatsApp for Windows allows sending Python and PHP attachments that are executed without any warning when the recipient opens them. For the attack to be ...
Tom's Hardware on MSN

Anthropic's model context protocol includes a critical remote code execution vulnerability

A design choice in the MCP SDKs allows remote code execution across the AI supply chain.