Python SDK could allow a malicious MCP server to steal OAuth authentication material and take over AI agent accounts. The ...

Cycode has disclosed a high-severity OAuth vulnerability in Anthropic’s official Model Context Protocol (MCP) Python SDK that ...

MCP Python SDK flaw can let malicious servers redirect OAuth exchanges and steal credentials; fixes are in 1.30.0 and 2.2.0.

I once needed to find emails containing a certain word from an old email archive (.pst). The conditions were the worst. Outlook was not installed. The file was 9.2GB. I couldn't build pypff (Python ...

A widespread smishing campaign was identified in which victims received fraudulent SMS messages impersonating official entities and were instructed to click a link inside the SMS in order to “complete ...

IntroductionIn June 2026, Zscaler ThreatLabz identified a new malware family, tracked as SloppyRAT, that is likely leveraged by a ransomware-related threat actor. ThreatLabz observed SloppyRAT being ...

Microsoft found a phishing campaign using ASCII smuggling, the invisible-character trick from AI prompt injection, to split words like funding.

Threat actors have adopted the ASCII smuggling technique in phishing campaigns, using invisible Unicode characters to evade email security filters.

Early on Thursday morning technical researcher Eric Lu sparked worldwide excitement and confusion by posting a sequence of 130 digits on X (formerly Twitter). The reason for the uproar over some ...

A clever technique used to hide malicious prompts in attacks on AI agents has been adopted by spammers to evade filters on email platforms that are designed to flag unwanted messages used in mass ...

Most of this week's trouble came dressed as something useful. A package stole data. A fake extension opened remote access. A safety app became spyware. An image gave hidden orders to an AI agent.