hackingincidents.ai
Incidents289Sources240Dataset2026-11-17Last sweep2026-11-17
Ledger / Oct 2026

Search-ad phishing hijacks cloud billing accounts for Gemini API usage

Confirmed

Wiz's incident response team handled the cases and its own report is cited.

Model
GeminiGoogle · closed
Agent harness
Nonechat or tool use only
Attributed country
Not attributedthe source names no country
Sectors hit
enterprise broadOrganisations with privileged Google Cloud (GCP) users and billing accounts

Attackers bought Google Search ads that led to fake Google logins, captured credentials and MFA codes, and linked their own GCP projects to victims' billing accounts to run Gemini API usage.

“Within 24 to 48 hours victim organisations saw charges of tens to hundreds of thousands of dollars in unauthorized Gemini API usage. Google Ads removed the malicious campaign after it was reported.”AI Threat Watch

Sources

Date
Oct 2026
Actor
Unknown actors (criminal), as attributed by AI Threat Watch
Targets
Organisations with privileged Google Cloud (GCP) users and billing accounts
What the AI did
LLMjacking, Phishing content
Model as named
Gemini
Model basis
A researcher names it
Autonomy
Assisted a human
Outcome
Victims saw tens to hundreds of thousands of dollars in unauthorized Gemini API charges within 24 to 48 hours.