CVE-2026-107858 json
Cross-Site WebSocket Hijacking and Permissive CORS in Google Agent Development Kit (ADK) for Java Development Server
published 17d ago modified 7d ago also EUVD-2026-108585
- cvss
- 7.2
- version 4.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 29%
- public exploits
- 0
- none known
Summary
Missing Origin Validation in WebSockets (CWE-1385) and Permissive Cross-domain Policy with Untrusted Domains (CWE-942) in the development web server (ADK Web) in Google Agent Development Kit (ADK) for Java (com.google.adk:google-adk-dev versions 0.1.0 before 1.13.0 and com.google.adk:google-adk-maven-plugin versions 0.3.0 before 1.13.0) allow a remote attacker to control a locally running agent and read its data via a malicious web page visited by a developer while the server is running. The /run_live WebSocket endpoint accepts connections from any origin by default (hardcoded via setAllowedOrigins("*") in versions 0.1.0 through 1.5.0, and defaulting to * via adk.web.cors.origins in versions 1.6.0 through 1.12.0), and since version 0.4.0 the REST API returns Access-Control-Allow-Origin: * by default. Because the server has no authentication and requests originate from the developer's browser (so binding to localhost does not prevent exploitation), a cross-origin page can send messages to the agent (triggering registered tools), stream agent responses, and list, read, create, or delete sessions and artifacts. In versions 1.6.0 through 1.12.0, users can mitigate the issue by setting the adk.web.cors.origins property to an explicit allowlist of trusted origins (such as http://localhost:8000). The vulnerability is fixed in version 1.13.0, which enforces a same-origin default for CORS and the /run_live WebSocket endpoint, and rejects DNS-rebinding requests over loopback.
Patch / fix
- Google Agent Development Kit (ADK) for Java 1.13.0
Is CVE-2026-107858 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerVendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-107858 updated cvss 7.6
com.google.adk/google-adk-dev: com.google.adk/google-adk-maven-plugin: google-adk: Unauthorized agent control via missing origin validation
-
Red Hat All currently supported Red Hat productsnot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 7d ago
Exploit prediction
0.36% chance of exploitation in the next 30 days, higher than 29% of all scored CVEs (FIRST EPSS, 2026-11-09).
Exploits and checks
- github.com https://github.com/google/adk-java/issues/1257 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 7.2 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:L/VA:L/SC:N/SI:N/SA:N |
| CNA | 4.0 | 7.2 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected products
- Google Agent Development Kit (ADK) for Java
Classification
References
-
github.com
/google/adk-java/commit/5667d382ab5078a0d6e8f7184713a6bab767e004
patch
-
github.com
/google/adk-java/commit/1ae5078072e13e101318e32833f1db323ef084e1
patch
-
github.com
/google/adk-java/pull/1222
mitigation, patch
-
github.com
/google/adk-java/commit/c2b087cbaf44f44d20dc946d8f2391506a2fce3d
mitigation, patch
-
github.com
/google/adk-java/issues/1257
issue-tracking, exploit
-
github.com
/google/adk-java/releases/tag/v1.13.0
release-notes
-
github.com
/google/adk-java/releases/tag/v1.6.0
release-notes
Sources
- CVE List CVE-2026-107858
- NVD CVE-2026-107858
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.