Back to skill

Security audit

Pipeworx nvd

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a simple NVD lookup connector, but its setup runs a mutable npm package automatically, so users should review the install path before enabling it.

Install only if you are comfortable running the npm-based MCP bridge under your user account. Prefer a pinned, reviewed `mcp-remote` version or a sandboxed MCP runtime before enabling this connector.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:25
Finding

Unpinned npm Package Is Downloaded and Executed Automatically

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 25-26
Vulnerability Type: Supply-chain risk through an unpinned executable dependency
Risk Level: Medium

Vulnerable Code

json
{
  "mcpServers": {
    "pipeworx-nvd": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://gateway.pipeworx.io/nvd/mcp"]
    }
  }
}

Technical Analysis

The configuration invokes npx with the -y option to download and execute mcp-remote@latest without interactive confirmation. The @latest tag is mutable and does not identify the exact package version that was reviewed. Consequently, the code executed on a future installation can differ from the code available at audit time.

If the npm package, its maintainer account, publication pipeline, or one of its transitive dependencies is compromised, an attacker could publish malicious code under a version selected by @latest. Package installation lifecycle scripts or the package executable could then run attacker-controlled code locally.

Attack Path

  1. An attacker compromises the mcp-remote package publication process, a maintainer account, or a relevant dependency.
  2. The attacker publishes a malicious release that becomes the package version resolved by the latest tag.
  3. A user enables the documented MCP configuration.
  4. npx -y retrieves the current package version without requesting confirmation.
  5. npm lifecycle code or the downloaded package executable runs with the privileges of the user operating the agent.
  6. The malicious process can access resources available to that user and may establish outbound communications or modify user-accessible files.

This path is conditional on a package or supply-chain compromise; the audited file does not itself contain a confirmed malicious payload.

Impact Assessment

Successful exploitation could provide arbitrary code execution with the privileges of the acc ...[truncated 412 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with a specifically reviewed, immutable version, such as mcp-remote@x.y.z.
  2. Record and verify package integrity using a lockfile, npm integrity metadata, or a trusted internal package mirror.
  3. Review the pinned package, its lifecycle scripts, and its complete transitive dependency tree before deployment.
  4. Disable or restrict npm lifecycle scripts where operationally possible.
  5. Execute the MCP process in a sandbox or container with minimal filesystem access, restricted environment variables, no administrative privileges, and tightly controlled outbound networking.
  6. Establish a controlled dependency-update process in which new versions are reviewed and tested before the pinned version is changed.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep