CVE-2025-59532Network attack vector

Sandbox escape via model-controlled writable root

Published Sep 22, 2025 · Updated Sep 23, 2025

Sandbox escape in OpenAI Codex CLI 0.2.0 through 0.38.0 allows attackers to write files beyond the workspace via a generated cwd. The command runner used one model-generated cwd for command execution and the sandbox writable-root policy instead of retaining the session's original boundary. Reachability requires a generated cwd outside the starting folder; resulting commands retain the Codex process's permissions, while network access remains blocked.

CVSS severity8.6
High
EPSS probability0.87%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Sandbox escape in OpenAI Codex CLI 0.2.0 through 0.38.0 allows attackers to write files beyond the workspace via a generated cwd. The command runner used one model-generated cwd for command execution and the sandbox writable-root policy instead of retaining the session's original boundary. Reachability requires a generated cwd outside the starting folder; resulting commands retain the Codex process's permissions, while network access remains blocked.

The record

CVE
CVE-2025-59532
Published
Sep 22, 2025
Updated
Sep 23, 2025
Vendor
OpenAI
Product
Codex
Classifications
CWE-20, T1059
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. Sep 22, 2025CVE publishedPublication date reported by the CVE source.
  2. Sep 23, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=>= 0.2.0, < 0.39.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

OpenAI · Codexversion=>= 0.2.0, < 0.39.0

Published CVSS scores

8.6OpenAICVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-20Improper Input Validation
T1059Command and Scripting Interpreter

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo