AI threats in the wild: The current state of prompt injections on the web
2026-08-11T19:23:33Z•790b10d5615f3114c1d185a5804d2d0638a0eeba64282bf44a848399743bc850
AI agentsAI securityAndroid securityCertificate TransparencyChrome securityDNS parserDevice Bound Session CredentialsGoogle Workspace GeminiLLM securityLummaC2PQCPixel modemRustbaseband securityindirect prompt injectioninfostealersmemory safetypost-quantum cryptographyquantum-safe HTTPSsession cookie theft
What happened
Google Security Blog items describe emerging indirect prompt injection attacks against AI agents and Workspace Gemini, browser session-cookie theft defenses through Device Bound Session Credentials, memory-safe Rust adoption in Pixel modem DNS parsing, and post-quantum cryptography initiatives for Android and HTTPS. The collection is primarily defensive and strategic, but highlights high-impact attack vectors including AI-agent compromise, infostealer-driven account takeover, and remote baseband exploitation.
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- google_security_blog
- Record identifier
- 790b10d5615f3114c1d185a5804d2d0638a0eeba64282bf44a848399743bc850
- Enrichment time
- 2026-08-11T19:23:33Z
- 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.