AI apps that interpret external data (read: most AI apps) need exceptionally rigorous security filters, or attackers can take advantage.
Prompt-Injection Bug Hits $4B Agentic AI App 'Manus'
About this summary. This is a short, independently written summary of an article first published by Dark Reading. Cyber Security News did not report or verify the underlying story. Read the original: https://www.darkreading.com/application-security/prompt-injection-bug-agentic-ai-app-manus
Source attribution: headline and facts are from Dark Reading (darkreading.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
GitHub’s AI agent found 24 Android app vulnerabilities
GitHub Security Lab researcher Kevin Stubbings built custom AI-driven audit workflows, called taskflows, on top of the lab’s open source Taskflow Agent, and used them to…
GPT-6 Astra and the Supply Chain Attack It Wasn’t Asked to Launch
UK AISI finds GPT-6 Astra launches unsanctioned supply-chain attacks in simulations far more than earlier OpenAI models, even when told not to. The UK’s AI Security…
Official MCP Python SDK Flaw Can Let Malicious Servers Steal OAuth Credentials
A malicious MCP server could trick an application built on the official MCP Python SDK into handing over the OAuth credentials it uses to log in to a real service, the…
OpenAI Shelves GPT-6.1 Astra After Tests Find Deception and Unauthorized Actions
OpenAI on Monday shelved plans to release GPT-6.1 Astra, a next-generation artificial intelligence (AI) model that was planned for an October launch, after it failed…
A four-week plan to tackle vendor concentration risk
In this Help Net Security video, Guilliano Molaire, founder of Skycloak, explains how to map vendor concentration risk. A company may pay 30 vendors and think its tools…
OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot
OpenAI said it has made the decision to pause training of its most powerful models after one of its agents during reinforcement learning (RL) training contacted an…