» Tag
ai-security
29 postsResearcher Tricks Claude Into Leaking User Secrets via Web Fetch
How a researcher exploited Claude's memory and web_fetch tool to silently exfiltrate a user's name, employer, and security answers letter by letter.
Enterprise AI Agents Are Now Runtime Products, Not Model Wrappers
Drawing on LangChain-NVIDIA's NemoClaw and Schneider Electric's LangSmith case study, this piece explains why enterprise AI agents are runtime products defined by permission boundaries, audit trails, and deployment—not just models.
AI Sandboxing: The Real Risk Lives in Infrastructure, Not the Model
As autonomous AI agents gain access to tools, credentials, and infrastructure, security focus is shifting from model behavior to runtime isolation and sandboxing.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comWriteOut Flaw in Writer AI Enabled Cross-Tenant Account Takeover
A critical flaw dubbed WriteOut let attackers hijack any Writer AI account by leaking session cookies through the platform's sandbox. Writer has since patched it.
The Lethal Trifecta Hiding in Your MCP Server, and How to Defuse It
An exploit-free attack on GitHub's MCP server reveals the 'lethal trifecta' risk in agent tooling, and the architectural fix engineers need.
AI's next phase: from smarter chat to controlled systems
HalluSquatting attacks, Prime Intellect's $130M raise, and DeepSeek's chip plans show AI advantage shifting from model choice to workflow control.
Shadow AI: You Can't Secure the AI Systems You Can't See
Enterprise AI adoption is outpacing visibility. A look at shadow AI risks and how an AI Bill of Materials helps discover, own, and govern hidden AI systems.
Prismata: Defending Web Agents Against Prompt Injection Attacks
Prismata introduces a new defense mechanism using dynamic trust labeling and content restriction to protect web agents from cross-site prompt injection attacks.
Defensive AI Coding Agents Hijacked via Prompt Injection for RCE
A PoC exploit shows how prompt injections in third-party code hijack Claude Code and Codex CLI to achieve remote code execution during defensive review.