BlackTreeCVE Intelligence
← Back to the CVE catalogue
Full vulnerability report · 2026
CVE-2026-64651High confidence

AI SDK OpenCode Harness Tool Relay Authorization Bypass

vercel · @ai-sdk/harness-opencode

Official source article: GitHub GHSA-G48P-5RR5-8RGQ ↗. Check the applicable product and release in the original source.

6.3MediumCVSS 4.0
Recommended action
Scheduled

Medium technical severity with no CISA KEV confirmation; remediate through the normal risk-based patch cycle unless local exposure raises the priority.

Fix not verified
R
Operational reassessment

Published severity in operational context

Open reassessment dashboard →
Published severityMediumOperational priority:Medium, unchanged from published severity.unchanged

Evidence used

  • No CISA KEV confirmation is currently recorded.
  • EPSS is 0.17% for the current model date.

Compensating controls

  • Restrict local access and enforce least privilege on affected hosts.
  • Monitor vendor guidance and exploitation sources for a material change.

Verification

  1. Confirm that the asset runs vercel @ai-sdk/harness-opencode and falls inside the recorded affected range.
  2. Recheck the vendor advisory before scheduling a change because no verified fixed version is currently retained.
  3. Validate exposure, authentication requirements and compensating controls in the actual environment.
  4. Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Mitigation target: As exposure requiresRemediation target: Within 365 days

This automated reassessment organises public evidence. It does not know asset exposure, business impact or control effectiveness and does not replace CVSS or a human risk decision.

Optional official sources

National CERT insights
?CERT means Computer Emergency Response Team; CSIRT is the closely related term Computer Security Incident Response Team.

Choose official national sources for this report. Each advisory shows its original language. Your selection is remembered on this device and included in shared links.

Official European source

ENISA European Vulnerability Database

Official EUVD identifiers, advisory evidence and known-exploited context. Missing fields are not treated as evidence of low risk.

1 current
ENISA EUVD identifier

EUVD-2026-46098

No EUVD known-exploited evidence

ENISA has published the identifier mapping but no EUVD description has been stored yet.

EUVD state
Present in the current official mapping
Known exploitation
Not present in the current ENISA EUVD known-exploited dataset. This is not proof of no exploitation.
ENISA score
Not supplied in the stored EUVD record
Advisory evidence
No linked advisory details stored yet
Recommended actionScheduled

Medium technical severity with no CISA KEV confirmation; remediate through the normal risk-based patch cycle unless local exposure raises the priority.

Fix not verified
01

What, why and how

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.

What

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.

Why

The application performs an authorisation check, but it does not correctly enforce the required permission boundary.

How

An attacker operating through local access may attempt exploitation without authentication or user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

What

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.

Why

The application performs an authorisation check, but it does not correctly enforce the required permission boundary.

How

An attacker operating through local access may attempt exploitation without authentication or user interaction. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

02

Exploit reality and attack path

CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.

Observed exploitation
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
No confirmed evidence

No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.

Public PoC / exploit material
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
None recorded

No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.

Likely attack path
local access → Incorrect Authorization → cause the confidentiality, integrity or availability impact described by the vendor
Attack surface
Local
Privileges required
None: unauthenticated exploitation is possible
User interaction
None
Attack complexity
Low: no specialised conditions are recorded
Security boundary
Not a CVSS 4.0 base metric
Weakness
?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-863 ↗

CWE-863: Incorrect Authorization. The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.

CVSS vector
?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
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

Common Vulnerability Scoring System 4.0: the compact vector below is decoded into plain language.

AVLocalAttack vector: The attacker needs local access to the vulnerable system.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.ATNoneAttack requirements: No additional deployment or execution condition is required.PRNonePrivileges required: The attacker does not need an account or existing privileges.UINoneUser interaction: No action by another user is required.VCNoneVulnerable-system confidentiality: No direct loss is represented by this metric.VILowVulnerable-system integrity: A successful attack can cause a limited loss.VANoneVulnerable-system availability: No direct loss is represented by this metric.SCHighSubsequent-system confidentiality: A successful attack can cause a major loss.SIHighSubsequent-system integrity: A successful attack can cause a major loss.SANoneSubsequent-system availability: No direct loss is represented by this metric.
Post-exploitation / living off the land
The issue can support a local privilege or sandbox boundary transition; normal system utilities may then be available in the gained context.
UnauthenticatedCWE-863
A

Official authority intelligence

Only matched European and national findings are included. Language selectors and unavailable sources are omitted.

Cyber Security Agency of Singapore · English · CSA-SB-20260722Security Bulletin 22 Jul 2026

The Cyber Security Agency of Singapore included this CVE in its official Security Bulletin 22 Jul 2026, published on 22 July 2026. Open the linked bulletin for the product, severity and reference information published in that issue.

Official advisory ↗
03

Patch and workaround

Operational remediation based on structured source evidence.

Status
?Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change.
Fix not verified
Affected
@ai-sdk/harness-opencode: < 1.0.29
Fixed
No fixed version is explicitly recorded in the structured CVE data.
Action
No verified patch reference is present in the current structured sources. Check the vendor advisory before making a change.
Workaround
No verified workaround is recorded. Limit untrusted access and use least privilege until authoritative guidance is available.
04

Evidence and provenance

Published 20 Jul 2026 · Last source change 21 Jul 2026, 12:49 UTC · CWE-863 · Incorrect Authorization

CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source
?The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.
FIRST · tracked since 2026-08-14
European sourceENISA EUVD · EUVD-2026-46098
Product sourceCNA
Remediation sourceCVE/CNA references
CWE sourceCNA
NVD statusNVD not scheduled

Core structured fields are present and their contributing authorities are shown above.

Material change intelligence

What changed after publication

View recent updates ↗

No material field changes have been recorded since change tracking began. Routine source refreshes and cosmetic edits are intentionally excluded.

Material fields only · duplicate refreshes suppressed · history retained for the configured operational retention period
CVE published
ENISA EUVD · EUVD-2026-46098↗CVE authority or vendor reference · GitHub GHSA-G48P-5RR5-8RGQ↗Official CVE record (CNA and ADP data)↗NVD record↗
Technical terms and abbreviations used in this report
CVE
Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
CVSS
Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
EPSS
Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
CWE
Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
CNA
CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
CISA ADP
Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
NVD
National Vulnerability Database: NIST's enrichment service for CVE records.
CERT / CSIRT
A computer security incident response team that publishes warnings or coordinates incident response.
PoC
Proof of concept: public material that demonstrates or helps reproduce exploitation.
CSAF
Common Security Advisory Framework: a machine-readable format for security advisories.
LoTL
Living off the land: abuse of legitimate tools or system functions during an attack.
Free version - for non-commercial use only.CVE-2026-64651 · cve.blacktree.nl