Kubernetes' standard security controls, such as RBAC and NetworkPolicies, are insufficient for protecting LLM agents from novel threats like prompt injection and model weight exfiltration. The CNCF ec…
A developer built a scanner that fires prompt-injection probes at a self-hosted AI agent and tested it across five model backends, finding leak rates ranging from 0% to 90% depending solely on the mod…
Enterprises are accumulating orphaned AI agents—autonomous tools left running after their creators depart—and standing privileges that increase attack surface, according to The Hacker News. Compromise…
A developer compiled a comprehensive defensive knowledge base cataloguing known prompt-injection and jailbreak patterns, the models and systems they have affected, and the defenses against them. The r…
AI-powered vulnerability discovery, as demonstrated by Mythos Preview, is shifting from sparse to dense sampling of software attack surfaces, potentially leaving attackers with fewer zero-day exploits…
WitnessAI launched Agentic Control on June 17, 2026, a single control plane to discover, monitor, govern, and restrict AI agent behaviors and their interactions with tools and Model Context Protocol (…
Microsoft released the Agent Governance Toolkit, a stateless policy engine built on Cedar that intercepts agent actions at sub-millisecond latency and covers all 10 OWASP Agentic Top 10 risks. However…
The Institute for Security and Technology published a policy paper Tuesday advocating for AI software bills of materials (AIBOMs) to reduce cyber risk and improve transparency. The paper argues that f…
Cybersecurity expert Chris Hughes discusses the rise of machine identities and agentic AI, emphasizing the need for new security measures to maintain trust as systems gain autonomy in enterprises.…
MAREF, a multi-agent AI security framework, addresses all 10 risks in the OWASP Agentic Top 10 threat model for multi-agent systems, including goal hijacking, tool misuse, and identity abuse, through …
A malicious PyPI package named 'ColorLib' was discovered targeting developers with info-stealing malware that exfiltrates environment variables, cryptocurrency wallet details, and credentials. OWASP r…
OWASP released AISVS 1.0, a security checklist with 514 verifiable requirements for AI systems, at Global AppSec Vienna. The standard fills a gap by providing testable controls for prompt injection, M…
Faultline Security offers manual penetration testing for startups and SaaS companies, priced from €3,000, to help them pass Series A security due diligence. The service provides clear scope, fixed pri…
Prompt injection remains the top LLM vulnerability on OWASP's Top 10 for LLM Applications across all editions, including the 2025 update. A developer with two years of production experience argues tha…
Last week saw active exploitation of a Check Point VPN zero-day vulnerability and attacks on Oracle PeopleSoft servers. Additionally, the open-source AI-powered Docker security scanner DockSec was rel…
A developer discovered that AI code generators like Cursor consistently omit ownership checks in API endpoints, leading to Insecure Direct Object Reference (IDOR) vulnerabilities. The AI correctly imp…
A developer has identified a persistent security threat to AI agents called memory poisoning, where malicious instructions stored in an agent's memory can influence all future interactions indefinitel…
Sujala Vasanthasena Nelavai used GitHub Copilot to identify and fix OWASP Authentication vulnerabilities as part of the GitHub Finish-Up-A-Thon challenge. The developer leveraged the AI assistant to i…
ShieldMCP launched a security scanner that analyzes MCP configuration files for permission risks, exposed secrets, and supply chain threats within 60 seconds. The tool scans across all OWASP MCP Top 1…
Security researchers chained multiple large language model and web application vulnerabilities during a red team exercise to escalate from a low-privileged account to full admin takeover. The attack e…