High-severity flaws in the Chainlit AI framework could allow attackers to steal files, leak API keys & perform SSRF attacks; ...

Researchers found the popular model context protocol (MCP) servers, which are integral components of AI services, carry ...

Update Chainlit to the latest version ASAP Two "easy-to-exploit" vulnerabilities in the popular open-source AI framework ...

Researchers with Cyata and BlueRock uncovered vulnerabilities in MCP servers from Anthropic and Microsoft, feeding ongoing security worries about MCP and other agentic AI tools and their dual natures ...

Server-side request forgery (SSRF) attacks consist of an attacker tricking the server into making an unauthorized request. The name itself implies that a request that should have otherwise been made ...

Researchers discovered the vulnerability in an API already integrated into many bank systems, which could have defrauded millions of users by giving attackers access to their funds. A server-side ...

Microsoft has fixed vulnerabilities in four separate services of its Azure cloud platform, two of which could have allowed attackers to perform a server-side request forgery (SSRF) attack — and thus ...

Security teams are warned to be on the lookout for a growing wave of opportunistic and largely untargeted cyber attacks exploiting two related exploit chains to target Microsoft Exchange servers. This ...