CVE-2026-64651: AI SDK OpenCode Harness Tool Relay Authorization Bypass

Severity: medium (CVSS 6.3 v4.0)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.2% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2026-07-20 · updated 2026-10-24
Weakness: CWE-863

Description

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.

Affected products

vercel @ai-sdk/harness-opencode: before 1.0.29

References

Get alerted when CVE-2026-64651 or the next vulnerability affects your stack