Summary
mcp-shell has a Secure Mode Allowlist Bypass via Default /bin/bash Executable
Impact
This is an OS Command Injection vulnerability (CWE-78). The shell_exec MCP tool is designed to execute only pre-approved executables; the bypass allows an attacker to run arbitrary commands present in the container image (curl, wget, env, sed, grep, tar, etc., all installed by the Dockerfile) under the identity of mcpuser (UID 1000).
Who is impacted:
- Any operator deploying the official Docker image without modifying the default
security.yamlis vulnerable immediately upon deployment. No custom configuration, no elevated privileges, and no prior authentication are required. - MCP clients that interact with a vulnerable
mcp-shellinstance, including automated AI agents, LLM orchestration platforms, and CI/CD pipelines, may be leveraged to exfiltrate secrets, tamper with files accessible tomcpuser, or pivot further within the container's network. - The
--network=noneflag used in the PoC demonstrates successful exploitation even with no network access; in production deployments with network access, the impact extends to data exfiltration and lateral movement.
Concrete consequences of exploitation:
- Confidentiality: Dump environment variables (
/bin/bash -c env), read files, or exfiltrate credentials visible tomcpuser. - Integrity: Write or modify files within the container's writable filesystem.
- Availability: Consume container resources or terminate processes.
Untrusted input reaches a shell command, allowing arbitrary commands to run on the host. Typical impact: code execution in the application's environment.
CVE-2026-55581 has a CVSS score of 8.4 (High). The vector is requires local access, no privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.6.0); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2026-55581? CVE-2026-55581 is a high-severity OS command injection vulnerability in github.com/sonirico/mcp-shell (go), affecting versions < 0.6.0. It is fixed in 0.6.0. Untrusted input reaches a shell command, allowing arbitrary commands to run on the host.
- How severe is CVE-2026-55581? CVE-2026-55581 has a CVSS score of 8.4 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of github.com/sonirico/mcp-shell are affected by CVE-2026-55581? github.com/sonirico/mcp-shell (go) versions < 0.6.0 is affected.
- Is there a fix for CVE-2026-55581? Yes. CVE-2026-55581 is fixed in 0.6.0. Upgrade to this version or later.
- Is CVE-2026-55581 exploitable, and should I be worried? Whether CVE-2026-55581 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-55581 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-55581? Upgrade
github.com/sonirico/mcp-shellto 0.6.0 or later.