Security readout for executives and security teams
Plain-English summary
CVE-2026-0760 is a critical remote code execution issue in Foundation Agents MetaGPT 0.8.1. An unauthenticated remote attacker could send crafted data that the application deserializes unsafely, allowing code to run as the service account. Treat exposed MetaGPT deployments as high-priority until vendor guidance or compensating controls are confirmed.
Executive priority
High priority. This is unauthenticated network remote code execution with critical CVSS impact. Prioritize finding MetaGPT 0.8.1, reducing exposure, and monitoring for vendor remediation. Do not assume exploitation is occurring unless new trusted sources confirm it.
Technical view
The flaw is in MetaGPT’s deserialize_message function and is classified as CWE-502: deserialization of untrusted data. The CVSS 3.0 score is 9.8, with network attack vector, low complexity, no privileges, and no user interaction. Successful exploitation can affect confidentiality, integrity, and availability in the service account context.
Likely exposure
Known affected product and version: Foundation Agents MetaGPT 0.8.1. Exposure is highest where MetaGPT services accept network-reachable untrusted input. The source data does not identify affected configurations, default exposure, or whether other versions are impacted.
Exploitation context
The advisory states authentication is not required and remote code execution is possible. The provided sources do not state active exploitation, and this CVE is not marked as KEV in the supplied data.
Researcher notes
Evidence is limited to the CVE record and ZDI advisory metadata. The root issue is unsafe deserialization in deserialize_message. No exploit details, patch version, or workaround is provided in the supplied sources. Avoid broad version assumptions beyond MetaGPT 0.8.1.
Mitigation direction
- Inventory MetaGPT deployments and identify any running version 0.8.1.
- Restrict network access to MetaGPT services until vendor guidance is confirmed.
- Monitor Foundation Agents and ZDI advisories for patches or official mitigation instructions.
- Run MetaGPT with least-privilege service accounts where operationally possible.
- Increase logging and monitoring around MetaGPT message handling and service process activity.
Validation and detection
- Confirm installed MetaGPT versions through approved asset or software inventory methods.
- Identify whether MetaGPT endpoints are reachable from untrusted networks.
- Review service account privileges used by MetaGPT processes.
- Check logs for unusual service crashes, process launches, or unexpected outbound connections.
- Track vendor advisories for clarification on fixed versions and affected ranges.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-502: Code execution behavior lookup
Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-0760 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.8 (3.0)
- Known Exploited
- No
- Published
Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H3.95.9Primary CVE scoreVulnerability scoring details
Base CVSS 3.0 score
9.8CriticalVector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Source materials
- CVE List V5 sourceCVE List V5
- ZDI-26-026CVE reference · x_research-advisory
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Deserialization of Untrusted Data
Deserialization of Untrusted Data represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.