Study finds AI agents can be tricked into executing attacker-controlled tool calls by echoing them back. Researchers also uncovered 253 verified security bugs across 118 open-source MCP servers.

Buying a shiny new platform isn’t consolidation until you actually switch off the old tools, which means asking the people ...

From escalating AI-enabled threats to persistent skills gaps, security leaders are reshaping their agendas to address several ...

Thousands of exposed DCGM Exporter instances leak GPU telemetry, and some also expose profiling endpoints that could let ...

For the third week running, Citrix has issued a critical security warning to customers managing their own NetScaler ADC and ...

Researchers successfully made GitHub Copilot CLI read sensitive local files and send their contents to an external endpoint.

The company has disclosed another CVSS severity 10 flaw in its internet-facing appliance, just months after a separate ...

The owner of a ransomware remediation company is facing trial for defrauding customers. Zohar Pinhasi, also known as “Zack ...

The 9.3-rated vulnerability lets unauthenticated attackers access specific files outside their intended boundaries. Atlassian ...

The US Federal Bureau of Investigation has removed an Accenture contractor working on its PeopleSoft installation over their role in a data breach that exposed personal details of FBI employees, ...

Attackers can replace phishing domains almost for free, so security teams should hunt for the servers and infrastructure that ...

Google's temporary halt on some bug bounty submissions underscores a broader problem facing enterprises: AI is making ...