Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax() and runPlaywrightTest() functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS command execution when an AI agent is induced to invoke these tools. Commit 88c77fc fixes these vulnerabilities.
Security readout for executives and security teams
Plain-English summary
Neo.mjs has a critical flaw that can let an attacker execute operating-system commands through its AI-facing file-system MCP server. Exploitation requires influencing an AI agent to invoke affected tools with a malicious path. Successful exploitation could compromise the confidentiality, integrity, and availability of the host running the server.
Executive priority
Treat this as an immediate remediation priority wherever the affected MCP server is deployed. Prioritize internet-facing, shared, or untrusted-content workflows first. If the component is not deployed, document that determination and monitor vendor guidance because the supplied version information is incomplete.
Technical view
CVE-2026-18482 is CWE-78 command injection in FileSystemService.mjs. The checkSyntax() and runPlaywrightTest() functions interpolate caller-controlled absolutePath values into shell commands without safe handling. The supplied record assigns CVSS 3.1 score 9.8 and identifies commit 88c77fc4 as the fix.
Likely exposure
Exposure is limited to deployments using the ai/mcp/server/file-system MCP server and its affected tools. Risk is highest where untrusted prompts or content can influence agent tool arguments. The supplied affected-version value is only "0," so the complete vulnerable release range cannot be determined from this bundle.
Exploitation context
The attack path involves inducing an AI agent to call checkSyntax() or runPlaywrightTest() with attacker-controlled input. The bundle marks this CVE as absent from KEV and provides no evidence of active exploitation. That absence does not establish that exploitation has never occurred.
Researcher notes
The central evidence is unsafe shell interpolation of absolutePath in two FileSystemService.mjs functions, with commit 88c77fc4 identified as corrective. CVSS indicates network reachability without privileges or user interaction, while the description still requires agent-mediated tool invocation. No KEV listing or active-exploitation evidence is supplied. Release-level affected and fixed versions remain unclear.
Mitigation direction
Apply the changes from vendor fix commit 88c77fc4.
Check Neo.mjs guidance for a release containing the fix.
Until patched, disable or tightly restrict the affected MCP tools.
Limit the MCP server process permissions and access to sensitive systems.
Prevent untrusted content from directly controlling MCP tool arguments.
Validation and detection
Inventory systems running the Neo.mjs file-system MCP server.
Determine whether checkSyntax() or runPlaywrightTest() is enabled or reachable.
Confirm deployed source includes the changes from commit 88c77fc4.
Review agent and MCP logs for unusual tool calls or path arguments.
Verify the MCP process operates with minimal filesystem and operating-system privileges.
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Potential ATT&CK relevance
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
cwe · medium confidence lookup
CWE-78: Command execution behavior lookup
Command injection weaknesses can lead defenders to review execution techniques and command interpreter telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
1CVSS vectors
3Timeline events
1ADP providers
4Source links
SSVC decision data
CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: pocAutomatable: yesTechnical Impact: total
CVSS vector scores
1 official score
We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
CWE-78 · source CWE mapping
Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.