Raw vector
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:XSummary
CVE-2026-64651 is a medium-severity Incorrect Authorization (CWE-863) vulnerability. Its CVSS base score is 6.3 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked at the 2th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
The strongest mitigations our analysis identified map to AC-24 (Access Control Decisions) and AC-25 (Reference Monitor) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-46098
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 5 hardening rules · 3 OS baselines
—
Mitigating Controls (NIST 800-53 r5) AI
AC-3 directly requires correct enforcement of authorization decisions on every access request, structurally preventing incorrect checks.
AC-24 ensures access-control decisions are made and applied consistently, reducing the chance of an incorrect authorization result.
A reference monitor that is always invoked and tamper-proof forces every authorization decision through a verified, correct path.
Least-privilege assignments shrink the set of authorizations that must be checked correctly, limiting exposure to flawed checks.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Defining, enforcing, and reviewing access authorizations and least privilege directly prevents incorrect authorization checks.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Requiring consistency between access rights and classification plus formal approval steps ensures that the authorization logic correctly distinguishes between entities that should and should not be granted access.
Enforcing policy-driven approval and role-change reviews stops incorrect or stale authorization decisions from remaining in effect after job changes or terminations.
By tying access rights to identity, device, location and classification, the control reduces the likelihood that an authorization decision will be based on an incorrect or bypassed policy.
Hardening callouts derived
Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).
Oracle Linux 8 (2 rules)
- V-248581 OL 8 must require users to provide a password for privilege escalation. prevents CWE-863
- V-252656 The OL 8 operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-863
RHEL 7 (1 rule)
- V-204430 The Red Hat Enterprise Linux operating system must be configured so that users must re-authenticate for privilege escalation. prevents CWE-863
RHEL 8 (1 rule)
- V-251712 The RHEL 8 operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-863