A tool designed to help ethical hackers bypass restrictive Content Security Policies
Securing CI/CD in an agentic world: Claude Code Github action case | Microsoft Security Blog
Microsoft Threat Intelligence identified a prompt injection pathway in Claude Code GitHub Action that allowed access to workflow secrets under specific conditions. This research examines the attack chain, responsible disclosure process, Anthropic's mitigation, and guidance for securing AI-powered CI/CD workflows.
Defeating Prompt Injections by Design
Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models are susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL uses a notion of a capability to prevent the exfiltration of private data over unauthorized data flows by enforcing security policies when tools are called. We demonstrate effectiveness of CaMeL by solving $77\%$ of tasks with provable security (compared to $84\%$ with an undefended system) in AgentDojo. We release CaMeL at https://github.com/google-research/camel-prompt-injection.
Hackers Expose Age-Verification Software Powering Surveillance Web
Three hacktivists tried to find a workaround to Discord’s age-verification software. Instead, they found its frontend exposed to the open internet.
Reducing XSS by way of Automatic Context-Aware Escaping in Template Systems
Posted by Jad S. Boutros, Security Team Building on our earlier posts on defenses against web application flaws [ "Automating Web Applicatio...
Tools from EFF's Tech Team
EFF’s team of technologists and computer scientists engineers solutions to the problems of sneaky tracking, inconsistent encryption, and more. Where users face threats to their privacy and security
Download pumping: New npm deception technique for supply chain attacks
Learn how attackers exploit automated bot traffic as part of software supply chain attacks to artificially inflate download counters and mask malicious payloads as legitimate.
Behind the Scenes Hardening Firefox with Claude Mythos Preview – Mozilla Hacks - the Web developer blog
New details about what we found, and how agentic harnesses are now able to reproduce real bugs and dismiss false positives.
Comment and Control: Prompt Injection to Credential Theft in Claude Code, Gemini CLI, and GitHub Copilot Agent
Anthropic Claude Code Security Review, Google Gemini CLI Action, and GitHub Copilot Agent are vulnerable to prompt injection via GitHub comments — turning PR titles, issue bodies, and issue comments into attack vectors for API key and token theft.
Microsoft “Digital Escorts” Could Expose Defense Dept. Data to Chinese Hackers — ProPublica
The Pentagon bans foreign citizens from accessing highly sensitive data, but Microsoft bypasses this by using engineers in China and elsewhere to remotely instruct American “escorts” who may lack expertise to identify malicious code.
Building a Browser-Native Verification Stack for Tinfoil
Learn how we built a browser-based confidentiality and integrity verifier with implementations of browser-native Sigstore and TUF libraries.
15 Open-Source Tools for Digital Sovereignty (2026) | Comparisons & Alternatives | Vucense
Own your digital stack. The 15 best open-source tools for privacy, security, and full control over your data — reviewed and ranked for 2026.
Stop Bill C-22!
🚨 Bill C-22 forces every Canadian internet provider, messaging app & cloud service to build surveillance backdoors and store a year of your data. Foreign state hackers exploited similar legislation in the US. Shut the backdoor: https://openmedia.org/StopC22 #BillC22
Hacker News: Honest Edition
GitHub MCP Exploited: Accessing private repositories via MCP
We showcase a critical vulnerability with the official GitHub MCP server, allowing attackers to access private repository data. The vulnerability is among the first discovered by Invariant's security analyzer for detecting toxic agent flows.
