prompt-injection

A public hacking challenge targeting an AI assistant powered by Claude Opus 4.6 resulted in zero successful prompt injection attacks across 6,000 attempts. The experiment cost $500 in API tokens and triggered a Google account suspension due to email volume, but no participants managed to extract the system's secrets.

OpenAI has expanded Lockdown mode to all ChatGPT plan tiers, including Free, Go, Plus, Pro, and Business users. The security feature blocks outbound network requests to prevent prompt injection attacks from stealing sensitive data, but disables live web browsing, Deep Research, and Agent mode.

OpenAI has released Lockdown Mode, an optional security setting that protects against prompt injection attacks by limiting network requests and image fetching in ChatGPT. The feature is designed for users handling sensitive data and disables some ChatGPT capabilities including Deep Research and Agent Mode.

Google announced Gemini Spark at I/O 2026, positioning it as a competitor to OpenAI's Claude-based agents. The service will integrate with Gmail, Calendar, Drive, and other Google apps, running on Gemini 3.5 Flash and a new platform called Antigravity. No general availability date has been disclosed.

Claude Code will automatically approve denied commands—like curl—if preceded by 50 or more chained subcommands, according to security firm Adversa. The vulnerability stems from a hard-coded MAX_SUBCOMMANDS_FOR_SECURITY_CHECK limit set to 50 in the source code, after which the system falls back to requesting user permission rather than enforcing deny rules.

A Google Deepmind paper introduces the first systematic framework for 'AI agent traps'—attacks that exploit autonomous agents' vulnerabilities to external tools and internet access. The researchers identify six attack categories targeting perception, reasoning, memory, actions, multi-agent networks, and human supervisors, with proof-of-concept demonstrations for each.

OpenAI has released IH-Challenge, a training dataset designed to teach AI models to reliably distinguish between trusted and untrusted instructions. Early results show significant improvements in security and prompt injection defense capabilities.

OpenAI is acquiring Promptfoo, an AI security platform, to integrate automated vulnerability testing directly into its Frontier enterprise offering. The acquisition adds jailbreak detection, prompt injection testing, and data leak identification capabilities to OpenAI's enterprise product.

Microsoft security researchers have identified a new prompt injection vulnerability where attackers embed hidden instructions in "Summarize with AI" buttons to permanently compromise AI assistant behavior and inject advertisements into chatbot memory.