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

2026-04-29T19:23:44Zcce9e30911ac4e5c90c6435b747a3d2eb951aec3bbef1de5aacb0703f1a37368
Android 17DBSCDNS parserGeminiGoogle WorkspaceIPILLM securityMerkle Tree CertificatesPKIPLANTSPQCPixel basebandRustVRPcertificate transparencycookie theftdevice bound session credentialsindirect prompt injectioninfostealermemory safetypost-quantum cryptographyprompt injectionquantum-safe HTTPSsession hijackingvulnerability rewards program

What happened

An aggregated Google Security Blog feed covering multiple April–March 2026 posts. Key topics: real-world discovery and analysis of indirect prompt injection (IPI) attacks against LLM integrations and Google Workspace (including defenses and continuous mitigations); rollout of Device Bound Session Credentials (DBSC) in Chrome to prevent cookie-based session theft; efforts to improve Pixel baseband memory safety by integrating a Rust DNS parser; Year-in-Review for Google’s Vulnerability Rewards Program (VRP); and platform-level moves toward post-quantum cryptography (PQC) in Android and quantum‑

Why it matters

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

Evidence and limitations

Source ID
google_security_blog
Record identifier
cce9e30911ac4e5c90c6435b747a3d2eb951aec3bbef1de5aacb0703f1a37368
Enrichment time
2026-04-29T19:23:44Z
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.

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