medium6.3
CVE-2026-6111
A security flaw has been discovered in FoundationAgents MetaGPT up to 0.8.1.
Impact
A security flaw has been discovered in FoundationAgents MetaGPT up to 0.8.1. This impacts the function decode_image of the file metagpt/utils/common.py. The manipulation of the argument img_url_or_b64 results in server-side request forgery. It is possible to launch the attack remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
Affected packages
| Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|
| pip | metagpt | <= 0.8.2 | none recorded |
Affected products
| Vendor | Product | Affected versions |
|---|---|---|
| Deepwisdom | Metagpt | Versions 0.8.0, 0.8.1 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/FoundationAgents/MetaGPT/
- https://github.com/FoundationAgents/MetaGPT/issues/1934
- https://github.com/FoundationAgents/MetaGPT/pull/1941
- https://vuldb.com/submit/791762
- https://vuldb.com/vuln/356971
- https://vuldb.com/vuln/356971/cti
- https://github.com/advisories/GHSA-r5v8-c28h-f8r8
- https://nvd.nist.gov/vuln/detail/CVE-2026-6111
- https://github.com/FoundationAgents/MetaGPT