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, ...
SecurityWeek

CrewAI Vulnerabilities Expose Devices to Hacking

Four vulnerabilities in CrewAI could be chained together via prompt injection for sandbox escape, remote code execution, and ...
CSOonline

Critical flaw in AI agent dev tool Langflow under active exploitation

Researchers from security firm Trend Micro warn that a critical remote code execution vulnerability patched in April in the Langflow AI agent framework is being exploited to deploy botnet malware. The ...
SecurityWeek

Cloudflare-Themed ClickFix Attack Drops Infiniti Stealer on Macs

A new ClickFix attack that leverages a Nuitka loader targets macOS users with the Python-based Infiniti Stealer malware.
CSOonline

Critical RCE bugs expose the n8n automation platform to host‑level compromise

A JavaScript sandbox bug rated CVSS 9.9 enables attackers to bypass AST‑based protections, while a Python execution bypass affects internal‑mode deployments common in enterprise setups. Two critical ...

Meta's new structured prompting technique makes LLMs significantly better at code review — boosting accuracy to 93% in some cases

This technique can be used out-of-the-box, requiring no model training or special packaging. It is code-execution free, which ...