mediumCVSS 7.3Vulnerability

CVE-2026-5971

A flaw has been found in FoundationAgents MetaGPT up to 0.8.1. This vulnerability affects the function ActionNode.xml_fill of the file metagpt/actions/action_node.py of the component XML Handler. Executing a manipulation can lead to improper neutralization of directives in dynamically evaluated code. The attack may be launched remotely. The exploit has been published and may be used. The project was informed of the problem early through a pull request but has not reacted yet.

Properties

severity
medium
summary
FoundationAgents MetaGPT vulnerable to eval injection
epss_score
0.00387
cvss_score
7.3
ghsa_published
2026-04-09T18:31:28Z
source_url
https://github.com/advisories/GHSA-3ghp-8r47-4gj4
ghsa_updated
2026-04-10T20:03:44Z
ghsa_id
GHSA-3ghp-8r47-4gj4
cve_id
CVE-2026-5971
cvss_vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
is_ghsa_only
false
epss_percentile
0.32096

Related Entities (5)

ENRICHED_BY (1)

[Source]FIRST EPSS

VULNERABLE_TO (1)

[Software]pip/metagpt

REPORTED_BY (1)

[Source]GitHub Advisory Database

AFFECTS (1)

[Software]pip/metagpt

HAS_WEAKNESS (1)

[Weakness]Improper Control of Generation of Code ('Code Injection')

Explore deeper with Ninja Signal's threat intelligence graph

CVE-2026-5971 (CVSS 7.3) — Ninja Signal Threat Intelligence | Ninja Signal