Last seen March 2, 2026

CVE-2026-0628 Privilege Escalation Vulnerability affecting Gemini

Evidence indicates that Gemini is affected by privilege escalation.

Technical Severity
Medium severity
Lifecycle Status

DEVELOPING

Sources

What Happened

Evidence indicates that Gemini is affected by privilege escalation.

Why This Matters

The evidence matters to defenders using Gemini because it could allow an attacker to gain additional privileges.

Recommended Action

No confirmed vendor remediation is available in the current evidence. Confirm whether Gemini is present in your environment and review the affected configuration.

Exposure

Recommended Response
First Seen

Feb 18, 2026 05:30

Last Seen

Mar 02, 2026 05:30

Exploitation status: UNKNOWN

Primary entities:

Google Gemini AI Agents Remote Code Execution CVE-2026-0628

Authoritative Intelligence

CVE CVE-2026-0628 Incident identifier
NVD CVSS 8.8 HIGH NVD
FIRST EPSS 0.067 93.3 pct
CWE CWE-862 Weakness classification

Provider evidence: NVD, OSV, FIRST EPSS

EPSS is a vulnerability exploitation probability signal, not proof that your environment is exposed. CISA KEV means known exploitation of the vulnerability, not that your system was exploited.

Timeline

  • Incident first seen
    Feb 18, 2026 05:30

    BugSkan first recorded this incident.

  • LLM-generated passwords 'fundamentally weak,' experts say - theregister.com
    Feb 18, 2026 05:30

    theregister.com · Vulnerability

  • Bug in Google's Gemini AI Panel Opens Door to Hijacking - Dark Reading
    Mar 02, 2026 05:30

    darkreading.com · Vulnerability

  • Latest observed development
    Mar 02, 2026 05:30

    Most recent source or update associated with this incident.

  • Material change
    Aug 18, 2026 14:07

    ACT -> REVIEW

  • Material change
    Aug 18, 2026 14:07

    recommended action updated

  • Material change
    Aug 18, 2026 14:07

    why it matters updated

  • Material change
    Aug 18, 2026 14:07

    severity 6.0 -> 6.5

Sources

LLM-generated passwords 'fundamentally weak,' experts say - theregister.com

theregister.com · Feb 18, 2026 05:30

LLM-generated passwords from tools like Claude, ChatGPT, and Gemini are "fundamentally weak" due to inherent patterns that make them highly predictable and easily guessable, despite appearing complex. Research indicates these passwords have significantly lower entropy (20-27 bits) compared to truly random ones, allowing them to be brute-forced in a matter of hours, potentially ushering in a new era of password brute-forcing.

Open publisher source
Bug in Google's Gemini AI Panel Opens Door to Hijacking - Dark Reading

darkreading.com · Mar 02, 2026 05:30

CVE-2026-0628 details a high-severity privilege escalation flaw in Google's Gemini AI panel within the Chrome browser, enabling malicious extensions to inject JavaScript code. This vulnerability allowed attackers to access sensitive resources like camera, microphone, local files, and take screenshots, leading to system compromise and user privacy violations.

Open publisher source

Watchlist Match

Want personalized relevance?

Create an account to see which incidents overlap with the technologies you monitor.

← Back to incident intelligence