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

2026-05-11T19:23:40Ze401cb96fe3145ff4d8bd8e1208ce04661abb6ea4ee308d69ed9837db701f426
Android 17Certificate Transparency (CT)DBSCDNS parserDevice Bound Session CredentialsGeminiGoogle WorkspaceIPILLM securityMTCMerkle Tree CertificatesPQCPixel basebandRustVRPVulnerability Rewards Programcookie theftindirect prompt injectioninfostealermemory safetymodem securitypost-quantum cryptographyprompt injectionquantum-safe HTTPSsession hijacking

What happened

Collection of Google Security Blog posts covering: active monitoring and defenses for Indirect Prompt Injection (IPI) and Google Workspace’s continuous mitigation efforts for LLM-targeted attacks; Pixel baseband hardening by integrating a memory-safe Rust DNS parser to reduce modem memory-safety vulnerabilities; rollout of Device Bound Session Credentials (DBSC) in Chrome to prevent session-cookie theft by malware; a 2025 Vulnerability Rewards Program (VRP) year-in-review; and platform-level cryptography work including Android’s phased Post-Quantum Cryptography (PQC) adoption starting in the A

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
google_security_blog
Record identifier
e401cb96fe3145ff4d8bd8e1208ce04661abb6ea4ee308d69ed9837db701f426
Enrichment time
2026-05-11T19:23:40Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.