MetaGPT CVE-2026-19059

Q: What is the CVSS score of CVE-2026-19059?

CVE-2026-19059 has a CVSS 4.0 base score of 1.9 (Low). CVSS vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.2%.

EUVD-2026-54294 LOW

Path Traversal (CWE-22)

2026-08-06 cna@vuldb.com

GHSA-x7c6-rrf2-hrj9

Path Traversal

1.9

CVSS 4.0 · Vendor: vuldb

Severity by source

Vendor (vuldb) PRIMARY

1.9 MEDIUM

CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

vuln.today AI

3.3 LOW

Local-only vector with low privileges required; impact is read-only limited confidentiality with no integrity or availability consequence per the description.

3.1 AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N

4.0 AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (vuldb).

CVSS VectorVendor: vuldb

Attack Vector

Local

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Lifecycle Timeline

Analysis Generated

Aug 06, 2026 - 23:15 vuln.today

DescriptionCVE.org

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. This affects the function read of the file metagpt/tools/libs/editor.py. This manipulation causes path traversal. The attack needs to be launched locally. The exploit has been publicly disclosed and may be utilized. The vendor was contacted early about this disclosure but did not respond in any way.

AnalysisAI

Path traversal in MetaGPT versions 0.8.0 through 0.8.2 (FoundationAgents) allows a local low-privileged attacker to read arbitrary files on the host system via the read function in metagpt/tools/libs/editor.py. Impact is limited to confidentiality - no write or availability impact is present. A public proof-of-concept exploit has been disclosed on GitHub; no vendor patch exists as the vendor did not respond to coordinated disclosure.

Technical ContextAI

MetaGPT is an LLM-based multi-agent framework where AI agents collaborate on software engineering tasks. The affected component is the read function in metagpt/tools/libs/editor.py, a tool that agents use to read filesystem content during task execution. CWE-22 (Path Traversal) identifies the root cause: the function accepts file path input without adequately sanitizing directory traversal sequences (e.g., ../), allowing input to escape the intended working directory scope and reference arbitrary files on the local filesystem. The CVSS 4.0 vector (AV:L/AC:L/AT:N/PR:L/UI:N/VC:L) confirms local-only reach, low privilege requirement, no special attack conditions, and limited confidentiality impact. No CPE strings were provided, but affected versions are explicitly identified as MetaGPT 0.8.0, 0.8.1, and 0.8.2 per EUVD-2026-54294.

RemediationAI

No vendor-released patch has been identified at time of analysis - the vendor did not respond to coordinated disclosure despite early contact. As a primary compensating control, deploy MetaGPT inside a container or chroot jail with filesystem access restricted strictly to required working directories, preventing traversal from reaching sensitive paths even if the vulnerability is triggered. Operators can also apply a local code patch normalizing file paths (e.g., using Python's os.path.realpath or pathlib.Path.resolve with a prefix check) before they are passed to the read function; this resolves the root cause but requires maintaining a fork. OS-level mandatory access controls (AppArmor profiles, SELinux policies, or seccomp filters) can restrict which files the MetaGPT process is permitted to open. Monitor application logs for traversal sequences (../) in file path arguments as a detection measure. Until an official patch is available, restrict local system access to MetaGPT deployments to trusted users only. Reference: VulDB advisory at https://vuldb.com/vuln/386516.