CVE-2026-64650
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.
⚡ Watch CVE-2026-64650
Get an email if CVE-2026-64650 is added to CISA KEV, gains public exploit code, or a new advisory cites it — max one per day, one-click unsubscribe.
Exploitation outlook
- Low exploitation risk0.11% 30-day exploitation probability — currently an unlikely target, but scores change as exploit code circulates. Riskier than 2% of all EPSS-scored CVEs.
Advisory coverage (1)
External references
Embed the live status
— this badge updates automatically when the KEV or exploit status changes. How to embed it →
[](https://www.csirts.com/cve/CVE-2026-64650)