How severe is CVE-2026-5970?

CVE-2026-5970 has a CVSS 3.x base score of 7.3, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is low, integrity low, and availability low.

Is CVE-2026-5970 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (31st percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2026-5970?

CVE-2026-5970 affects Deepwisdom Metagpt. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-5970?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.

Does CVE-2026-5970 have an EU (EUVD) identifier?

Yes. CVE-2026-5970 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-20984.

When was CVE-2026-5970 published?

CVE-2026-5970 was published on 2026-04-09 and last updated on 2026-06-17.

CVE-2026-5970

CVE-2026-5970 is a high-severity vulnerability in Deepwisdom Metagpt with a CVSS 3.x base score of 7.3. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-74.

Key facts

Severity: High (CVSS 3.x base score 7.3)
CVSS v2: 7.5
CVSS v4: 5.5
EPSS exploit prediction: 0% (31st percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-20984
Weakness: CWE-74
Affected product: Deepwisdom Metagpt
Published: 2026-04-09
Last modified: 2026-06-17

Description

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.

Frequently asked questions

What is CVE-2026-5970?: A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.
How severe is CVE-2026-5970?: CVE-2026-5970 has a CVSS 3.x base score of 7.3, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is low, integrity low, and availability low.
Is CVE-2026-5970 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (31st percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-5970?: CVE-2026-5970 affects Deepwisdom Metagpt. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-5970?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
Does CVE-2026-5970 have an EU (EUVD) identifier?: Yes. CVE-2026-5970 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-20984.
When was CVE-2026-5970 published?: CVE-2026-5970 was published on 2026-04-09 and last updated on 2026-06-17.

References

Affected products (1)

cpe:2.3:a:deepwisdom:metagpt:*:*:*:*:*:*:*:*

More vulnerabilities in Deepwisdom Metagpt

CVE-2026-0761 — Critical (CVSS 9.8): Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability. This…
CVE-2026-0760 — Critical (CVSS 9.8): Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability.…
CVE-2024-23750 — High (CVSS 8.8): MetaGPT through 0.6.4 allows the QaEngineer role to execute arbitrary code because RunCode.run_script() passes shell…
CVE-2026-6110 — High (CVSS 7.3): A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. This affects the function generate_thoughts of…
CVE-2026-5974 — High (CVSS 7.3): A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.1. The affected element is the function Bash.run…
CVE-2026-5973 — High (CVSS 7.3): A vulnerability was found in FoundationAgents MetaGPT up to 0.8.1. Impacted is the function get_mime_type of the file…

All CVEs affecting Deepwisdom Metagpt →

Other CWE-74 (Improper Neutralization of Special Elements (Injection)) vulnerabilities

CVE-2026-25586 — Critical (CVSS 10.0): SandboxJS is a JavaScript sandboxing library. Prior to 0.8.29, a sandbox escape is possible by shadowing hasOwnProperty…
CVE-2026-25520 — Critical (CVSS 10.0): SandboxJS is a JavaScript sandboxing library. Prior to 0.8.29, The return values of functions aren't wrapped.…
CVE-2025-20265 — Critical (CVSS 10.0): A vulnerability in the RADIUS subsystem implementation of Cisco Secure Firewall Management Center (FMC) Software could…
CVE-2025-20337 — Critical (CVSS 10.0): A vulnerability in a specific API of Cisco ISE and Cisco ISE-PIC could allow an unauthenticated, remote attacker to…
CVE-2025-20281 — Critical (CVSS 10.0): A vulnerability in a specific API of Cisco ISE and Cisco ISE-PIC could allow an unauthenticated, remote attacker to…
CVE-2024-42472 — Critical (CVSS 10.0): Flatpak is a Linux application sandboxing and distribution framework. Prior to versions 1.14.0 and 1.15.10, a malicious…

Browse all CWE-74 (Improper Neutralization of Special Elements (Injection)) vulnerabilities →