This popular AI agent could be hacked by a single email — with potentially disastrous consequences

Researchers found a way around Manus' guardrails and got it to execute a simple email prompt injection attack.

What are Claude Code mods? A guide to the differences from Skills and MCP, official examples, and how to get started｜使い魔工房

When working with Claude Code, you might find yourself wondering, "How much conversation information has accumulated?", "What ...

How does the Claude Code workflow differ from sub-agents? 4 ways to choose based on 'who holds the plan'

How many agents have you ever run simultaneously in Claude Code?I've run up to 13, and lost 3 of them within the same day.The ...
MIXED Reality News

Claude Code 2.1.287 adds mods, and Anthropic says they can read your API key

Anthropic published Claude Code 2.1.287 to npm on October 1 at 16:59 UTC, and the new thing in it is Claude Mods: plugins ...
xenospectrum

OpenAI-Linked AI Agents Appear to Have Chained Outside Web Services to Extend Restricted Access, Investigation Finds

Asymmetric Security's follow-up probe into activity tied to OpenAI's agents examines a chain of external browser and ...
THE DECODER

Claude Code's new Mods system lets developers rewrite the AI coding tool from the inside

Anthropic is adding a "Mods" system to Claude Code, essentially middleware that runs directly inside the tool. Developers can ...

Salt Labs Research: A Single Email Could Hijack an AI Agent and Reach a User's Connected Accounts

Salt Security, the leader in agentic and API security, today published new Salt Labs research, revealing how a single malicious email could have hijacked the Manus agentic AI platform and exposed ...
news.ssbcrack

Twitch Chat Message Exploit Reveals Vulnerability in OBS Studio Leading to Native Code Execution

A significant security vulnerability affecting Twitch streamers has been uncovered, enabling a malicious chat message to ...