Signal criticality: High
What happened: Help Net Security reported that it can work with files uploaded manually. It can work with files uploaded manually. Anamarija Pogorelec , Senior Staff Writer, Help Net Security June 8, 2026 Share OpenAI is locking down parts of ChatGPT to reduce data theft risks OpenAI has started rolling out Lockdown Mode for ChatGPT , an optional security setting that restricts access to external resources and several product capabilities. It is available for personal accounts, including Free, Go, Plus, and Pro plans, as well as self-serve ChatGPT Business accounts.
Key takeaways:
Original source: https://www.helpnetsecurity.com/2026/06/08/openai-lockdown-mode-available/
Signal criticality: High
What happened: The Decoder AI reported that but a manipulative instruction hidden in an uploaded file can still influence the model's behavior and lead to wrong answers, OpenAI says. The feature blocks all connections to the internet and external services, preventing sensitive data from being leaked during conversations with the AI. Users can activate Lockdown Mode in the security settings and temporarily disable it for individual conversations when broader functionality is needed. Ask about this article… Search With the new Lockdown Mode, ChatGPT users can disable web access, Deep Research, and Agent Mode to better protect themselves against data theft through prompt injection attacks.
Key takeaways:
Original source: https://the-decoder.com/chatgpts-new-lockdown-mode-lets-you-disable-web-access-and-more-to-protect-sensitive-data-from-prompt-injection/
Signal criticality: High
What happened: The Hacker News published "AI Agent Uncovers 21 Zero-Days in FFmpeg; Chrome Patches Record 429 Bugs". Two things landed within days of each other this week. A security startup reported 21 previously unknown vulnerabilities in FFmpeg, the media library inside almost everything that touches video, all of them found by an autonomous AI agent. The same week, Google shipped Chrome 149 with patches for 429 security bugs, the most ever in a single release. Only the FFmpeg bugs were found by AI The article focuses on governance, identity, guardrails, or permission boundaries around AI agents that can act with real system access.
Key takeaways:
Original source: https://thehackernews.com/2026/06/ai-agent-uncovers-21-zero-days-in.html
The strongest signal today is that AI security is being decided in the surrounding control layer — permissions, connectors, deterministic workflow design, response speed, and the infrastructure that still underpins trust. That is a more durable framing than generic agent hype, and it is the one worth carrying forward.