Claude Flaw Automatically Sends Malicious Prompts to AI Agents
A vulnerability, dubbed ‘PromptFiction,’ has been discovered in Anthropic’s Claude Desktop application, allowing attackers to automatically submit malicious prompts to the AI assistant with a single click, bypassing the need for user interaction. This flaw, combined with a previous vulnerability (‘Claudy Day’), could lead to data exposure, code execution, and remote access on a victim’s machine. Anthropic has released a fix (version 1.1.2321), and experts emphasize the need for organizations to proactively manage AI agent risk, treating them as a form of ‘shadow IT’ and implementing robust monitoring and control measures around agent API traffic and access.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data
