AI SDK Codex Harness Tool Relay Authorization Bypass

published 2026-07-20 3 mo ago modified 2026-10-24 15 d ago also EUVD-2026-46102

cvss: 6.3; version 4.0, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.2%; EPSS 0.2% chance of exploitation in 30 days, percentile 6%
public exploits: 0; none known

The `@ai-sdk/harness-opencode` tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path (the Codex CLI shim). This allows untrusted code executing in the sandbox to invoke arbitrary host-exposed tools, including secret lookups, deployment operations, and cloud API calls without a corresponding model-authorized tool-call event. Exploitation requires a Linux environment (the vulnerable fallback checks `process.platform === 'linux'` and reads `/proc`); an active harness session with one or more host-provided tools; and untrusted code executing in the sandbox (e.g. a malicious dependency, build script, or lifecycle hook) The fix in version 1.0.29 removes the process-path authorization fallback entirely. Relay requests are now only accepted after exact, short-lived, one-time authorization matching the tool name and input from a bridge-observed model event. Some workarounds are available. Do not run the Codex harness on untrusted repositories or with untrusted dependencies, and/or limit host-exposed tools to non-sensitive operations when working with untrusted code.

Patch / fix

links 1

github.com/vercel/ai#17105 pull request

CISA SSVC

Exploitation: none
Automatable: no
Technical impact: partial
Assessed: 3 mo ago (2026-07-20)

Exploit prediction

0.17% chance of exploitation in the next 30 days, higher than 6% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CNA	4.0	6.3	CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:H/SI:H/SA:N
CNA	4.0	6.3	CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:H/SI:H/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

vercel @ai-sdk/harness-codex

Classification

Weakness

CWE-863 Incorrect Authorization

References

Sources

CVE List CVE-2026-64650
NVD CVE-2026-64650

Fencer Vulns 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.

Summary