Developer Fernando Irarrázaval challenged attackers to trick his AI assistant, Fiu, into leaking a secrets.env file using prompt injection. Running on OpenClaw with Anthropic's Claude Opus 4.6, Fiu withstood over 6,000 emails from 2,000 attackers, including attempts by 'Pliny the Liberator,' demonstrating robust AI security against a top threat.
A new study by researchers from Nanyang Technological University and other institutions reveals that AI agents are highly vulnerable to prompt injection attacks, with direct attacks succeeding over 79% of the time. The research highlights the risk of 'stealthy parasitism,' where AI agents advance attacker objectives while completing user tasks.
Microsoft researchers found a vulnerability in Anthropic's Claude Code GitHub Action that could expose credentials in software development pipelines via prompt injection attacks, now patched.
OpenAI releases Lockdown Mode for ChatGPT to reduce prompt injection attack risks by limiting web access and features, targeting sensitive data handlers.
OpenAI releases Lockdown Mode, an optional security feature to protect against prompt injection attacks, particularly for users handling sensitive data, by limiting certain features in ChatGPT.
