The path traversal flaw, allowing access to arbitrary files, adds to a growing set of input validation issues in AI pipelines.

As generative AI cements its place in enterprise software development, a familiar discipline is taking on new urgency: risk management. For decades, securing code has relied on understanding the ...

Security researchers at BeyondTrust Phantom Labs discovered a critical flaw in OpenAI's Codex coding agent that allowed an ...

Microsoft SharePoint, a core platform for enterprise collaboration, is facing active exploitation through a newly confirmed ...

Citrix has patched two NetScaler ADC and NetScaler Gateway vulnerabilities, one of which is very similar to the CitrixBleed ...

Researchers are warning about the risks posed by a low-cost device that can give insiders and hackers unusually broad powers in compromising networks. The devices, which typically sell for $30 to $100 ...

Device code phishing attacks that abuse the OAuth 2.0 Device Authorization Grant flow to hijack accounts have surged more ...

As AI systems become embedded in software development, the threat landscape is expanding. Prompt injection is one of the ...

Oracle's recent layoffs highlight a shift towards AI-driven coding, reshaping the tech workforce and redefining the role of ...

Four vulnerabilities in CrewAI could be chained together via prompt injection for sandbox escape, remote code execution, and ...

Researchers managed to steal GitHub OAuth tokens by abusing a command injection vulnerability.

While rising adoption of AI agents is certainly encouraging when it comes to productivity and enterprise efficiency, the ...