CVE-2026-64651
The @ai-sdk/harness-opencode tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path (host-tool-mcp.mjs). 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 1.0.28 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 OpenCode 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-2026-64651
Get an email if CVE-2026-64651 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-2026-64651)