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

2026-08-31T13:23:36Z07b599da9a3f36d9dc003e145aaa7715825ea89353a6f220483ad3854bfae60b
AI-agentsAI-securityAndroidCertificate-TransparencyChromeDNS-parserGeminiGoogle-WorkspaceHTTPSLLM-securityLummaC2PQCPixelRustbrowser-securitycellular-basebanddevice-bound-session-credentialsindirect-prompt-injectioninfostealersmemory-safetypost-quantum-cryptographyprompt-injectionsession-cookie-theftvulnerability-rewards-program

What happened

Google security research and product updates cover real-world indirect prompt injection threats against AI agents and Workspace Gemini, browser session-cookie theft protections using Device Bound Session Credentials, memory-safe Rust adoption in Pixel modem DNS parsing, post-quantum cryptography migration for Android and HTTPS, and Google’s vulnerability rewards program. The material describes threat trends, defensive engineering, and future-facing security architecture rather than a specific disclosed vulnerability.

Why it matters

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

Evidence and limitations

Source ID
google_security_blog
Record identifier
07b599da9a3f36d9dc003e145aaa7715825ea89353a6f220483ad3854bfae60b
Enrichment time
2026-08-31T13:23:36Z
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.