An indirect prompt injection could be chained with a sandbox bypass and Cursor’s remote tunnel feature for shell access to machines.
The post Cursor AI Vulnerability Exposed Developer Devices appeared first on SecurityWeek.
OpenAI Widens Access to Cybersecurity Model After Anthropic’s Mythos Reveal
GPT‑5.4‑Cyber is a model fine-tuned for defenders, lowering boundaries for legitimate cybersecurity work.
The post OpenAI Widens Access to Cybersecurity Model After Anthropic’s Mythos Reveal appeared first on SecurityWeek.
Artemis Emerges From Stealth With $70 Million in Funding
The startup is leveraging AI to prevent AI-powered attacks across applications, users, machines, and cloud workloads.
The post Artemis Emerges From Stealth With $70 Million in Funding appeared first on SecurityWeek.
Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments
A researcher has disclosed the details of the AI attack method he has named ‘Comment and Control’.
The post Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments appeared first on SecurityWeek.
Capsule Security Emerges From Stealth With $7 Million in Funding
The Israeli startup aims to secure AI agents at runtime, continuously monitoring their behavior to prevent unsafe actions.
The post Capsule Security Emerges From Stealth With $7 Million in Funding appeared first on SecurityWeek.
‘By Design’ Flaw in MCP Could Enable Widespread AI Supply Chain Attacks
Researchers warn that a flaw in Anthropic’s Model Context Protocol allows unsanitized commands to execute silently, enabling full system compromise across widely used AI environments.
The post ‘By Design’ Flaw in MCP Could Enable Widespread AI Supply Chain Attacks appeared first on SecurityWeek.
‘Mythos-Ready’ Security: CSA Urges CISOs to Prepare for Accelerated AI Threats
CISOs face a shrinking window to prepare as AI models like Mythos collapse the gap between vulnerability discovery and exploitation, driving a new era of high-velocity cyberattacks.
The post ‘Mythos-Ready’ Security: CSA Urges CISOs to Prepare for Accelerated AI Threats appeared first on SecurityWeek.
OpenAI Impacted by North Korea-Linked Axios Supply Chain Hack
The AI giant is taking action after determining that a macOS code signing certificate may have been compromised.
The post OpenAI Impacted by North Korea-Linked Axios Supply Chain Hack appeared first on SecurityWeek.
Apple Intelligence AI Guardrails Bypassed in New Attack
RSAC researchers hacked Apple Intelligence using the Neural Exect method and Unicode manipulation.
The post Apple Intelligence AI Guardrails Bypassed in New Attack appeared first on SecurityWeek.
Can we Trust AI? No – But Eventually We Must
From hallucinations and bias to model collapse and adversarial abuse, today’s AI is built on probability rather than truth, yet enterprises are deploying it at speed without fully understanding the risks.
The post Can we Trust AI? No – But Eventually We Must appeared first on SecurityWeek.
