Advisory record · GHSA-rg7c-g689-fr3x

Google Agent Development Kit (ADK) has a Code Injection and Missing Authentication vulnerability

CVSS 9.3 CriticalCriticalEPSS 0.022 · 82nd percentile

Critical, because:

  • CVSS score 9.3: 9.0 or more.

How we decide what’s critical

Published by the GitHub Advisory Database at 29 Jun 2026, 11:50 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
google-adkPyPI>=1.7.0, <1.28.1 || >=2.0.0a1, <2.0.0a21.28.1, 2.0.0a2
Identifiers
GHSA-rg7c-g689-fr3x · CVE-2026-4810 · PYSEC-2026-344
Weakness (CWE)
CWE-306
Published
29 Jun 2026
Updated
2 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

Google Agent Development Kit (ADK) versions 1.7.0 through before 1.28.1, and 2.0.0a1 through before 2.0.0a2, are affected by a code injection flaw with missing authentication. An unauthenticated remote attacker can execute arbitrary code on the server hosting the ADK instance. Upgrade google-adk to 1.28.1 or 2.0.0a2, and redeploy the upgraded version to production environments, along with any local ADK Web instance.

Written 10 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
9.3 Critical 4.0 CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:P/U:Amber CNA (GoogleCloud)
  • CISA KEV Not listed.
  • EPSS 0.022, the 82nd percentile, on 17 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

This record came from the full history of the GitHub Advisory Database, published 29 Jun 2026. New records show when each source confirmed them.

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.