MetagptApplication · Deepwisdom

CVE-2026-0760

CRITICAL · 9.8 CVSS v3.0 Published 2026-01-23
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability. The specific flaw exists within the deserialize_message function. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28121.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

The vulnerability exists in MetaGPT's Foundation Agents within the deserialize_message function, which deserializes user-supplied data without proper validation. This unsafe deserialization allows remote attackers to execute arbitrary code in the context of the service account without authentication.

MitigationImplement proper input validation and use safe deserialization methods (e.g., JSON instead of pickle/yaml unsafe formats, or whitelisted classes) in the deserialize_message function; restrict network exposure since no authentication is required.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
MetagptApplication
Affected:= 0.8.1

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Verify MetaGPT installation and version
    Run 'pip show metagpt' or check your package manager to identify the installed version of the metagpt package
    Affected if The installed version is exactly 0.8.1
  2. Locate deserialize_message function
    Search the metagpt installation directory for the file containing deserialize_message function (typically in agent-related modules under the Foundation Agents component)
    Affected if The deserialize_message function exists and uses pickle, yaml, or similar unsafe deserialization methods on user-supplied data
  3. Inspect deserialization implementation
    Examine the deserialize_message function code to confirm it directly deserializes data without validating the source or using unsafe formats like pickle/yaml without safe loaders
    Affected if The function deserializes data without proper input validation or uses unsafe deserialization formats
  4. Check network exposure
    Determine if the MetaGPT service is accessible over a network without authentication (e.g., exposed API endpoint, web service, or network service)
    Affected if The service is exposed to network access without requiring authentication, allowing remote attackers to send malicious serialized data

You are affected if you have MetaGPT version 0.8.1 installed AND the deserialize_message function uses unsafe deserialization AND the service is network-accessible without authentication.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

From vendor data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Implement proper input validation and use safe deserialization methods (e.g., JSON instead of pickle/yaml unsafe formats, or whitelisted classes) in the deserialize_message function; restrict network exposure since no authentication is required.

Fix this in Metagpt Scoped from the published advisory
  • Consultation4.0 h
  • Implementation12.0 h
  • Testing8.0 h
  • Review / QA4.0 h
28.0 hours of engineering $4,880
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $7,808.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-0760 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-0760 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data