#prompt injection
87 stories taggedprompt injection · page 6 of 6.
Prompt Injection in Git Repos Can Turn Claude Code Into a Reverse Shell Launcher
Malicious instructions buried in a repository's files can hijack Anthropic's Claude Code agent and open a backdoor on the developer's own machine, no obvious malware required.
North Korean Malware Tells AI Analyzers to Look Away
A macOS sample attributed to Pyongyang-linked actors contains prompts designed to make LLM-assisted security tools abandon their analysis. Defenders are starting to notice the pattern.
MCP's Enterprise Overhaul Hands Security Problems to Developers
A major revision to the Model Context Protocol repositions itself as enterprise-ready, then quietly offloads the hard security work onto the teams building on top of it.
Gaslight: A Rust macOS Stealer That Tries to Talk Your AI Analyst Out of Looking
The implant ships with an embedded prompt injection payload aimed at LLM-assisted reverse engineering tools, a small but telling escalation in adversarial tradecraft.
AI Agents Are Being Manipulated Through the Data They Trust
Hidden content injections and context poisoning are turning autonomous AI pipelines into attack surfaces. What defenders need to understand before deploying agents at scale.
Agentic AI Runs on Context. Feed It the Wrong Kind and Decisions Go Sideways Fast.
The core vulnerability in agentic AI systems isn't the model, it's the context window. Bad inputs, machine-speed outputs.
When the Trigger Pulls Itself: Agentic AI and the End of the Human-in-the-Loop
Every weapon in history extended a human decision. Agentic systems are the first that try to replace it, and the security implications are not theoretical.
Zero Trust as the AI Control Plane: What Zscaler's Vienna Pitch Means for APAC CISOs
AI agents are joining the workforce whether security teams are ready or not. At Zenith Live 2026, Zscaler made its case for why zero trust should govern them the same way it governs humans.
SearchLeak Shows How a Single Crafted URL Can Drain Your M365 Tenant
Varonis researchers chained three weaknesses in Copilot Enterprise Search into a full data-exfiltration path. Microsoft patched it. The attack class isn't going anywhere.
AI Web Agents Have No Reliable Prompt Injection Defenses, Benchmark Finds
Researchers ran 3,168 adversarial tests against GPT-5 and Gemini-powered agents. The 'Robust Behavior' outcome, agent completes task, attacker gets nothing, never appeared.
Twelve Controls That Actually Matter Once AI Ships to Production
Visibility into AI applications is a starting point, not a security posture. Here is what ongoing monitoring and defense of production AI systems looks like in practice.
OpenAI's Lockdown Mode Admits the Problem It Can't Quite Fix
The new containment feature reduces AI-enabled data exfiltration but doesn't stop it. Experts are divided on whether enterprises should trust a vendor to police itself.