Skip to main content
EPSS 0.2%top 91%

CVE-2026-55580: CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in sonirico mcp-shell

0
High
VulnerabilityCVE-2026-55580cvecve-2026-55580cwe-78
Published: 08/25/2026 (08/25/2026, 15:42:36 UTC)
Source: CVE Database V5
Vendor/Project: sonirico
Product: mcp-shell

Description

CVE-2026-55580 is an OS command injection vulnerability in sonirico's mcp-shell prior to version 0.6.0. The vulnerability arises because the default configuration disables security checks, allowing unrestricted OS command execution by any connected client. This insecure default state is documented and results from the absence of a security policy file. The issue is fixed in version 0.6.0.

CVSS v4.0

Score 8.6high

Attack Vector
Local
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
High
Vuln. Integrity
High
Vuln. Availability
High
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Affected software

sonirico

mcp-shell

Affected versions
<0.6.0

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/10/2026, 04:22:44 UTC

Technical Analysis

The mcp-shell product, a server for running shell commands securely and auditably, had a security flaw before version 0.6.0 where the Security.Enabled flag was initialized to false by default. When the environment variable MCP_SHELL_SEC_CONFIG_FILE is unset, the application starts without a security policy, causing the SecurityValidator.validateCommand function to allow all commands without restriction. This enables an attacker, such as an LLM connected over stdio, to execute arbitrary OS commands as the mcp-shell process user. The insecure default configuration is documented in the README and client setup instructions. The vulnerability is addressed in version 0.6.0.

Potential Impact

An attacker with access to the mcp-shell service can execute arbitrary OS commands with the privileges of the mcp-shell process user due to the lack of command validation in the default insecure configuration. This can lead to full system compromise depending on the process privileges. There are no known exploits in the wild reported.

Mitigation Recommendations

Upgrade to mcp-shell version 0.6.0 or later, where the security policy enforcement is enabled by default and the vulnerability is fixed. Until upgraded, explicitly configure MCP_SHELL_SEC_CONFIG_FILE to a valid security policy file to avoid running in the insecure default state.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-06-16T23:18:03.169Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6a8dba54acd9273b4965b600

Added to database: 08/25/2026, 15:52:52 UTC

Last enriched: 09/10/2026, 04:22:44 UTC

Last updated: 10/07/2026, 18:48:21 UTC

Views: 39

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

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

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses