2026-04-23 · 2026-Q2

Google Workspace Reports 32% Rise in Indirect Prompt Injection Pages on the Open Web

Outside the model: ContextAgent tooling was not the attack surface, so no layer applies.

Fixable: Unknown
Vendor response: Unknown
In the wild: No
Actor: Not applicable

Target

Public web content consumed by AI agents and Google Workspace Gemini integrations (sector-wide measurement based on Google's 2-3 billion crawled pages per month)

Impact

Google observed a 32% relative increase in malicious indirect prompt injection pages between November 2025 and February 2026; payloads target agentic AI features that can send email, run terminal commands, or process payments; Forcepoint amplified the same finding with field cases

Root cause

AI agents ingest untrusted web content with no strict data versus instruction boundary; static blogs, forums, and comment sections are now intentional weaponization surfaces for IPI

Sources

Catalog

View this entry in the catalog

Cite this: AgentProv incident record: Google Workspace Reports 32% Rise in Indirect Prompt Injection Pages on the Open Web (2026-04-23). https://agentprov.com/incidents/2026-04-23-google-workspace-reports-32-rise-in-indirect-prompt-injection-pages-on-the-open