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

2026-05-08T19:23:43Z881772ab04eeb2e0ede2e845e54013de4c917521fbac1b99514a71cd961ca098
AI securityAndroid 17ChromeDBSCDNS parserDevice Bound Session CredentialsGoogle WorkspaceIPIMTCMerkle Tree CertificatesPQCPixel basebandRustVRPVulnerability Rewards Programcookie theftindirect prompt injectioninfostealermemory safetypost-quantum cryptographyquantum-safe HTTPS

What happened

This collection of Google Security Blog posts highlights multiple high-impact threats and corresponding mitigations. Threat Intelligence observed active indirect prompt injection (IPI) activity on the public web and identifies IPI as a primary attack vector against AI agents; Google Workspace and other teams are adopting continuous, defense-in-depth mitigations to reduce IPI risk. Chrome and Google Account teams released Device Bound Session Credentials (DBSC) to prevent stolen/exfiltrated cookies from being reused (Windows Chrome 146 available; macOS coming). Pixel teams are integrating a new

Why it matters

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

Evidence and limitations

Source ID
google_security_blog
Record identifier
881772ab04eeb2e0ede2e845e54013de4c917521fbac1b99514a71cd961ca098
Enrichment time
2026-05-08T19:23:43Z
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.