Product
Gemini API
- First Reported
- Feb 28, 2026
- Latest Reported
- Nov 2, 2026
Reported Context (6)
- Bedrock, Gemini API, etc.). Once enabled, the threat actor can use the APIs to generate massive bills to the organization in just minutes or hours. Mandiant Details LLMJacking Attacks Monetizing Compromised Cloud LLM Access
- Enable the Gemini API product Wiz Details GCP Attacks That Hijack Cloud Billing for Unauthorized LLM Use
- In late 2025, Google's threat researchers disclosed PROMPTFLUX, an experimental dropper that queries the Gemini API roughly once an hour to regenerate fresh, obfuscated versions of itself. How AI-Driven Polymorphic Malware Challenges Signature-Based Detection
- Its “Thinking Robot” component queries the Gemini API to request fresh VBScript obfuscation and evasion code, instructing the model to act as an “expert obfuscator” and rewriting its entire source roughly every hour to Why Morphisec Says Self-Modifying Malware Challenges Detection-First Defenses
- In February 2026, Truffle Security published research revealing that when the Gemini API (Generative Language API) is enabled on a Google Cloud project, every existing API key on that project silently gains access to Hardcoded Android App Keys Can Expose Gemini API Access and User Files
CVE (1)
Malware (6)
People (2)
Threat Actors (1)
MITRE ATT&CK (20)
Vendors (7)
Products (37)
Tools (6)
Industries (4)
Countries (3)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
