A vulnerability was found in FoundationAgents MetaGPT up to 0.8.2. (CVE-2026-19058)
A vulnerability was found in FoundationAgents MetaGPT up to 0.8.2. The impacted element is the function DataInterpreter of the file metagpt/roles/di/data_interpreter.py. The manipulation results in code injection. The attack must be initiated from a local position. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.
AI Analysis
Technical Summary
FoundationAgents MetaGPT versions prior to 0.8.3 contain a code injection vulnerability in the DataInterpreter function located in metagpt/roles/di/data_interpreter.py. This vulnerability allows an attacker with local access and limited privileges to inject code, potentially impacting confidentiality, integrity, and availability. The vulnerability is tracked as CVE-2026-19058 and has a CVSS v3.1 base score of 5.3 (AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L). The vendor was notified but did not respond, and no official patch has been released. Public exploit code exists, but no confirmed exploitation in the wild has been observed.
Potential Impact
Successful exploitation can lead to code injection by a local attacker with low privileges, potentially resulting in limited confidentiality, integrity, and availability impacts. The attack cannot be initiated remotely and requires local access. The overall severity is low based on CVSS scoring.
Mitigation Recommendations
No official patch or remediation has been published by the vendor. Since the vulnerability requires local access and privileges, restricting local access to trusted users and monitoring for suspicious local activity is advisable. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance.
A vulnerability was found in FoundationAgents MetaGPT up to 0.8.2. (CVE-2026-19058)
Description
A vulnerability was found in FoundationAgents MetaGPT up to 0.8.2. The impacted element is the function DataInterpreter of the file metagpt/roles/di/data_interpreter.py. The manipulation results in code injection. The attack must be initiated from a local position. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.
CVSS v3.1
Score 5.3medium
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
FoundationAgents MetaGPT versions prior to 0.8.3 contain a code injection vulnerability in the DataInterpreter function located in metagpt/roles/di/data_interpreter.py. This vulnerability allows an attacker with local access and limited privileges to inject code, potentially impacting confidentiality, integrity, and availability. The vulnerability is tracked as CVE-2026-19058 and has a CVSS v3.1 base score of 5.3 (AV:L/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L). The vendor was notified but did not respond, and no official patch has been released. Public exploit code exists, but no confirmed exploitation in the wild has been observed.
Potential Impact
Successful exploitation can lead to code injection by a local attacker with low privileges, potentially resulting in limited confidentiality, integrity, and availability impacts. The attack cannot be initiated remotely and requires local access. The overall severity is low based on CVSS scoring.
Mitigation Recommendations
No official patch or remediation has been published by the vendor. Since the vulnerability requires local access and privileges, restricting local access to trusted users and monitoring for suspicious local activity is advisable. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-5j3c-8q7x-589c
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-19058"]
- Database Specific Severity
- LOW
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6a7573a5bf8831d539d92942
Added to database: 08/07/2026, 05:56:53 UTC
Last enriched: 08/07/2026, 08:16:11 UTC
Last updated: 09/21/2026, 22:01:32 UTC
Views: 100
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.