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

2026-08-15T19:23:32Z4551833138bedfde0a943261b2e183c9d0ecfab1de2aa9392658e4efb26e896d
AI-agentsAI-securityAndroidCertificate-TransparencyChromeDNS-parserDevice-Bound-Session-CredentialsGeminiGoogle-WorkspaceHTTPSLLM-securityLummaC2PQCPixelRustTLSbrowser-securitycellular-basebandindirect-prompt-injectioninfostealermemory-safetypost-quantum-cryptographyprompt-injectionquantum-securitysession-cookie-theft

What happened

Google security publications describe active and emerging security concerns, including indirect prompt injection against AI agents and Workspace Gemini, browser session-cookie theft and defenses via Device Bound Session Credentials, memory-safety hardening of Pixel modem firmware with Rust, post-quantum cryptography migration in Android and HTTPS certificate infrastructure, and broader vulnerability research and rewards. These are primarily defensive guidance and threat-intelligence disclosures rather than reports of a specific exploitable 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
4551833138bedfde0a943261b2e183c9d0ecfab1de2aa9392658e4efb26e896d
Enrichment time
2026-08-15T19:23:32Z
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.