Hackers Use Hidden Website Instructions in New Attacks on AI Assistants
Cybersecurity researchers at Forcepoint uncover new indirect prompt injection attacks that use hidden website code to exploit AI assistants like GitHub Copilot.
github
Scenario: Open-source framework for automated AI app red-teaming
Enterprises running customer service bots, data analytics agents, and other AI-driven applications in production handle sensitive records and connect to core business systems every day. LangWatch has released Scenario, an open-source framework that run…
PentAGI: Open-source autonomous AI penetration testing system
Penetration testers have long relied on collections of specialized tools, manual coordination, and documented runbooks to work through a target assessment. PentAGI, an open-source project from VXControl, attempts to automate that entire workflow using …
SmokedMeat: Open-source tool shows what attackers do inside CI/CD pipelines
Boost Security has released SmokedMeat, an open-source framework that runs attack chains against CI/CD infrastructure so engineering and security teams can see what an attacker would do in their specific environment. What the tool does SmokedMeat takes…
New CGrabber and Direct-Sys Malware Spread Through GitHub ZIP Files
Hackers spread CGrabber and Direct-Sys malware through GitHub ZIP files, bypassing security tools to steal passwords, crypto wallets, and user data.
GitHub lays out copyright liability changes and upcoming DMCA review for developers
A U.S. Supreme Court ruling issued in March has settled a question that has circulated among platform operators and developers for years: whether a service provider can be held liable for copyright infringement committed by its users without evidence o…
Legitify: Open-source scanner for security misconfigurations on GitHub and GitLab
Misconfigured source code management platforms remain a common entry point in software supply chain attacks, and organizations often lack visibility into which settings put them at risk. Legitify, an open-source tool from Legit Security, addresses that…
ZeroID: Open-source identity platform for autonomous AI agents
ZeroID is an open-source identity platform that implements an identity and credentialing layer specifically for autonomous agents and multi-agent systems. The attribution problem The core issue ZeroID targets is attribution in agentic workflows. When a…
Hackers Exploit GitHub Copilot Flaw to Exfiltrate Sensitive Data
A high-severity flaw in GitHub Copilot Chat recently allowed attackers to silently steal sensitive data like API keys and private source code. Tracked as CVE-2025-59145 with a critical CVSS score of 9.6, this vulnerability required no malicious code ex…
Asqav: Open-source SDK for AI agent governance
AI agents are executing consequential tasks autonomously, often across multiple systems and with little record of what they did or why. Asqav, a Python SDK released under the MIT license, addresses that gap by attaching a cryptographic signature to eac…