ActiveState explains how GitHub Actions attack chains can evade traditional CI security scanners, why passing a scan doesn't ...

Crews are racing to find survivors under rubble Russia targets Kyiv in air strikes for the second time in a week.

As reports of the blasts came in, state television said the Syrian president had welcomed Macron at the presidential palace.

Opera GX patched a flaw that let malicious sites silently install GX Mods and leak a signed-in user’s Gmail address with CSS.

A critical flaw discovered in the Opera GX browser could enable malicious websites to automatically install a customization ...

Discover the AI Agent Safety Directory that evaluates AI agents before deployment with trusted safety ratings, risk insights, and performance benchmarks.

A prompt injection attack can trick GitHub’s preview Agentic Workflows into retrieving content from private repositories and ...

Zscaler found attackers using SEO poisoning and hidden prompts in malicious websites to manipulate AI agents into making cryptocurrency payments.

Indirect prompt injection attacks are now draining cryptocurrency from AI agents in production. Zscaler ThreatLabz documented ...

Named after BioShock's 'Would you kindly' mechanic, the attack trains AI agents to accept false information before stealing ...

A critical prompt injection vulnerability in GitHub Agentic Workflows could allow unauthenticated attackers to leak private repository data, ...

Attackers have begun embedding hidden instructions in websites to target AI agents, according to new research. Zscaler's ...