AI threats in the wild: The current state of prompt injections on the web

Collection of Google Security Blog posts covering emerging AI and platform security work: Google Threat Intelligence highlights indirect prompt injection (IPI) as a high-priority real-world attack vector and reports web monitoring for IPI patterns while Google Workspace implements continuous defenses. Other posts announce security improvements across Google products: integrating Rust for a memory-safe DNS parser in the Pixel baseband to reduce memory-safety bugs; Device Bound Session Credentials (DBSC) rolling out to mitigate cookie/session theft from infostealers; a VRP (Vulnerability Rewards