# CVE-2026-5970: FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection

> Remote attackers can execute arbitrary code via the check_solution function in MetaGPT benchmarks, requiring immediate attention from users of this library.

- **Severity:** Medium 6.9 (`CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 9 Apr 2026
- **Updated:** 9 Apr 2026
- **Also known as:** GHSA-g977-h85w-h2xj, PYSEC-2026-2640

## What is CVE-2026-5970?

CVE-2026-5970 is a medium-severity code injection vulnerability in FoundationAgents MetaGPT, published on 9 Apr 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official 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.

Weakness: CWE-94 (Improper Control of Generation of Code), CWE-74 (Improper Neutralization of Special Elements in Output Used by a Downstream Component)

## Which versions are affected by CVE-2026-5970?

3 open source packages ship an affected version, including metagpt. It affects 1 product.


| Package | Ecosystem | Affected | Fixed in |
| --- | --- | --- | --- |
| `metagpt` | PyPI | All versions to 0.8.1 | None |
| `metagpt` | PyPI | All versions to 0.8.1 | None |
| `metagpt` | PyPI | All versions to 0.8.1 | None |

Products: Deepwisdom Metagpt.

## How do I fix CVE-2026-5970?

No fix has been published for CVE-2026-5970 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-5970 being exploited?

It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-5970 exists.

## Other vulnerabilities in FoundationAgents MetaGPT

- [CVE-2026-0760](https://insights.sbomify.com/CVE-2026-0760/): Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability (critical 9.8)
- [CVE-2026-0761](https://insights.sbomify.com/CVE-2026-0761/): Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability (critical 9.8)
- [CVE-2024-23750](https://insights.sbomify.com/CVE-2024-23750/): Code execution in metagpt (high 8.8)
- [CVE-2026-6110](https://insights.sbomify.com/CVE-2026-6110/): FoundationAgents MetaGPT Tree-of-Thought Solver tot.py generate_thoughts code injection (medium 6.9)
- [CVE-2026-5971](https://insights.sbomify.com/CVE-2026-5971/): FoundationAgents MetaGPT XML action_node.py ActionNode.xml_fill eval injection (medium 6.9)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-5970 and fix it if it is affected.

What it is: CVE-2026-5970 is a medium-severity code injection vulnerability in FoundationAgents MetaGPT, published on 9 Apr 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-5970 exists.

Affected packages and fixed versions:
- metagpt (PyPI): affected all versions up to 0.8.1; no fix listed
- metagpt (PyPI): affected all versions up to 0.8.1; no fix listed
- metagpt (PyPI): affected all versions up to 0.8.1; no fix listed

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-5970/ (Markdown: https://insights.sbomify.com/CVE-2026-5970/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-5970
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-5970
- OSV: https://osv.dev/vulnerability/CVE-2026-5970

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-5970/
Summaries are generated and may contain mistakes; the official description above is the record.