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, ...
Docker has released security fixes for a critical vulnerability affecting its AI-assisted feature known as Ask Gordon. The issue could allow attackers to trigger arbitrary code execution under certain ...
Anthropic PBC’s official Git Model Context Protocol server has several security vulnerabilities that can lead to arbitrary file access and, in some scenarios, full remote code execution triggered ...
The U.S. Cybersecurity & Infrastructure Security Agency (CISA) is warning of hackers exploiting an arbitrary code execution flaw in the Git distributed version control system. The agency has added the ...
Google has released a Chrome security update addressing two high-severity vulnerabilities that could allow attackers to execute arbitrary code or cause browser crashes. The issues affect core browser ...
A newly disclosed flaw in Anthropic’s Claude Desktop Extensions shows how a routine productivity feature can enable zero-click system compromise. LayerX researchers found that a single malicious ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results