» Tag
cybersecurity
69 postsInvestigating Three Real-World Incidents in Cybersecurity Evaluations
Details on three incidents involving the Claude model's unauthorized access during cybersecurity evaluations.
OpenAI's GPT-Red: A Super Hacker LLM for Enhanced Model Security
OpenAI's GPT-Red is a super-hacker LLM that automates security testing, enhancing model defenses against cyber threats.
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.
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.comOpenAI Launches Patch the Planet for Open Source Security
OpenAI and Trail of Bits unveiled Patch the Planet, pairing AI-driven vulnerability discovery in open source with mandatory human expert review before patches ship.
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.
Canadian Tax Lure Expands into a 46-Country RMM Campaign
A remote access campaign, initially targeting Canada with fake tax documents, has expanded to 46 countries, with 45% of activity in the US.
GLM-5.3 arrives with advanced cyber capabilities and finds vulnerability in Cursor
Z.ai's GLM-5.3 model has launched, finding a serious vulnerability in Cursor and showcasing advanced cybersecurity capabilities.
Zero Risk Isn't the Job: A CISO's Guide to Agentic AI
A guide for CISOs on managing agentic AI risks and ensuring security governance.
AI Doesn't Break Security, It Reprices It
AI is reshaping cybersecurity by undermining economic assumptions. This shift has critical implications for engineers in risk analysis and system design.
Anthropic's Mythos Model Detects Critical Vulnerability in Rejetto HFS
Anthropic's Mythos model uncovers a critical vulnerability in Rejetto HFS. Users are urged to update to secure versions.