Back to skill

Security audit

Pipeworx countries

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent country-data connector, but its setup runs a mutable third-party package with local user privileges without pinning or confirmation.

Review this before installing. The country lookup behavior is straightforward, but prefer a pinned, reviewed mcp-remote version or a locked local installation, and run the MCP bridge with only the permissions it needs.

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:50
Finding

Unpinned Third-Party Package Is Downloaded and Executed Automatically

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 50–55
Vulnerability Type: Unpinned and automatically executed third-party dependency
Risk Level: Medium

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

Technical Analysis

The configuration invokes npx with both the -y option and the mutable dependency specifier mcp-remote@latest. When the configuration is used, npx may download the package version currently associated with the npm latest tag and execute its code without interactive confirmation.

Because latest can resolve to different package contents over time, the effective executable is not reproducible and can change after this Skill has been reviewed. If the npm package, its publisher account, or its release process is compromised, a malicious version could execute locally with the permissions of the user running the Agent.

Attack Path

  1. An attacker compromises the mcp-remote package, a maintainer account, or its publication pipeline.
  2. The attacker publishes a malicious release and associates it with the mutable latest tag.
  3. A user installs or launches the documented MCP configuration.
  4. npx -y resolves and downloads the malicious release without requesting confirmation.
  5. Package lifecycle or runtime code executes with the Agent user's local privileges.
  6. The malicious code can access resources available to that user or manipulate communications between the Agent and the remote MCP endpoint.

Impact Assessment

Successful exploitation could result in arbitrary code execution under the account running the Agent. The accessible scope may include readable user files, environment variables, locally available credentials, and Agent or MCP configuration. The package could also alter or intercept MCP requests and respon ...[truncated 218 chars]

Remediation
View remediation

Remediation Suggestions

  • Replace mcp-remote@latest with an exact, reviewed version such as mcp-remote@x.y.z.
  • Verify the selected package version and publisher before use.
  • Install the dependency through a lockfile-controlled workflow and validate its registry integrity hash.
  • Avoid npx -y for security-sensitive setup because it suppresses installation confirmation.
  • Prefer invoking a previously installed, reviewed local binary rather than downloading executable code at launch.
  • Run the MCP bridge with least privilege in a restricted environment that limits filesystem, credential, and network access.
  • Establish a controlled update process in which new dependency versions are reviewed and tested before the pinned version is changed.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

Example: countries that speak Arabic

bash
curl -s -X POST https://gateway.pipeworx.io/countries/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"countries_by_language","arguments":{"language":"arabic"}}}'