CVE Tools

CVE-2026-64651

AI SDK OpenCode Harness Tool Relay Authorization Bypass

No known exploitation. EPSS puts it in the 5th percentile. No fix published yet.

Published Updated Sources: CVE.org, NVD

What to do

No fixed build or workaround is published yet. Limit exposure and watch for a patch.

What it is

From the CVE record

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.

In plain language

No plain-language summary for this CVE yet.

Exploitation

Where each signal puts this CVE on the scale from published to confirmed exploited.

EPSS5th
CISA KEV

Not in the catalog. CISA has not confirmed exploitation.

Public exploits

No public exploit or proof of concept found in the sources we track.

EPSS

0.2% chance of exploitation activity in the next 30 days, which ranks it in the 5th percentile of scored CVEs.

Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.

Lifecycle

6 events over 3 days, from the signal feeds we watch.

  1. Record updated
  2. Record updated
  3. Publishedweakness classified, att&ck mapped, record updated

Affected products

Technical detail

Weaknesses

ATT&CK techniques

Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.

Sources

Watch the software you run.

My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.

We'll flag the next CVE, public exploit or patch for @ai-sdk/harness-opencode, not every advisory.

We use analytics cookies to see which pages and articles actually help people. Decline and none of them run — the site works the same. What we store