AI threats in the wild: The current state of prompt injections on the web
2026-06-21T07:23:39Z•b96b4e96d0711cb7a97561d4c0a0cf5e1cc752d1a115297620f53628d59bfd0a
Android 17DBSCDNS parserDevice Bound Session CredentialsGoogle WorkspaceIPILLM securityMerkle Tree CertificatesPQCPixel basebandRustVRPVulnerability Rewards Programagentic automationcertificate transparencycookie theftgenai securityindirect prompt injectioninfostealersmemory safetymodem securitypost-quantum cryptographyprompt injectionquantum-safe HTTPSsession hijacking
What happened
This Google Security Blog collection highlights multiple high-priority defensive efforts and emerging threats: researchers found active indirect prompt injection (IPI) patterns in the wild and Google is continuously hardening LLMs (Workspace/Gemini) against IPI; Pixel modem firmware is being hardened by integrating a memory-safe Rust DNS parser; Chrome is rolling out Device Bound Session Credentials (DBSC) to prevent cookie/session theft from infostealers; the Vulnerability Rewards Program (VRP) 2025 review and continued platform hardening are summarized; Android is beginning phased rollouts/β
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- google_security_blog
- Record identifier
- b96b4e96d0711cb7a97561d4c0a0cf5e1cc752d1a115297620f53628d59bfd0a
- Enrichment time
- 2026-06-21T07:23:39Z
- 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.