CVE-2026-6110 FoundationAgents MetaGPT Tree-of-Thought Solver tot.py generate_thoughts code injection
Remote attackers can execute arbitrary code via the Tree-of-Thought Solver in MetaGPT due to improper neutralization of special elements.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-6110?
CVE-2026-6110 is a medium-severity code injection vulnerability in FoundationAgents MetaGPT, published on 12 Apr 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
A vulnerability was identified in FoundationAgents MetaGPT up to 0.8.1. This affects the function generate_thoughts of the file metagpt/strategy/tot.py of the component Tree-of-Thought Solver. The manipulation leads to code injection. It is possible to initiate the attack remotely. The exploit is publicly available and might be used. The project was informed of the problem early through an issue report but has not responded yet.
Which versions are affected by CVE-2026-6110?
3 open source packages ship an affected version, including metagpt. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
metagpt PyPI | All versions to 0.8.2 | None |
metagpt PyPI | All versions to 0.8.2 | None |
metagpt PyPI | All versions to 0.8.2 | None |
Products include Deepwisdom Metagpt.
How do I fix CVE-2026-6110?
No fix has been published for CVE-2026-6110 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-6110 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-6110 exists.
Other vulnerabilities in FoundationAgents MetaGPT
- CVE-2026-0760 Foundation Agents MetaGPT deserialize_message Deserialization of Untrusted Data Remote Code Execution Vulnerability
- CVE-2026-0761 Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability
- CVE-2024-23750 Code execution in metagpt
- CVE-2026-5970 FoundationAgents MetaGPT HumanEvalBenchmark/MBPPBenchmark check_solution code injection
- CVE-2026-5971 FoundationAgents MetaGPT XML action_node.py ActionNode.xml_fill eval injection
Sources
Also known as GHSA-xr7v-m9px-q4qj, PYSEC-2026-2645.