Back to skill

Security audit

Pipeworx holidays

Security checks for vulnerabilities and agentic risk

Overview

This holiday lookup skill is straightforward, but its setup runs a mutable npm package locally, which should be reviewed before installation.

Install only if you are comfortable with a remote holiday service and a locally executed npm MCP bridge. Prefer pinning `mcp-remote` to a reviewed exact version, running it with limited filesystem and environment access, and avoiding sensitive data in holiday lookup requests.

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:47
Finding

Unpinned npm Package Is Downloaded and Executed Automatically

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 47–53
Vulnerability Type: Unpinned third-party dependency execution
Risk Level: Medium

Vulnerable Code

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

Technical Analysis

The MCP configuration invokes npx with both -y and the mutable package reference mcp-remote@latest. This causes npm to resolve, download, and execute the package selected by the latest tag without an interactive confirmation step.

Because the dependency is not pinned to a reviewed version, the code executed during setup can change after the skill has been audited. If the npm package, its publisher account, or a transitive dependency is compromised, a malicious release can be distributed through the same configuration. There is no evidence in the reviewed file that the package is currently malicious; the vulnerability is the unsafe supply-chain execution mechanism.

Attack Path

  1. An attacker compromises the mcp-remote npm publisher, package, or one of its dependencies.
  2. The attacker publishes a malicious release and causes the latest tag to resolve to it.
  3. A user or agent applies the documented MCP configuration.
  4. npx -y mcp-remote@latest downloads the compromised release without requesting confirmation.
  5. npx executes the package with the privileges and environment of the agent process.
  6. The malicious package can access resources available to that process and execute further commands.

Impact Assessment

Successful exploitation could result in arbitrary local code execution under the account running the MCP server. Depending on that account's permissions and runtime isolation, an attacker could read accessible files and environment variables, steal credentials, modify user-owned data, initiate network connections, or install additional payloads. Th ...[truncated 148 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with an exact, reviewed package version rather than a mutable distribution tag.
  2. Install the dependency locally through a lockfile-backed workflow and preserve npm integrity metadata.
  3. Review the pinned package and its transitive dependency tree before deployment.
  4. Use automated dependency monitoring, but require review and testing before version upgrades.
  5. Avoid npx -y where practical so unexpected downloads do not execute without confirmation.
  6. Run the MCP bridge in a sandbox or restricted service account with minimal filesystem, environment-variable, process, and network access.
  7. Consider using a trusted internal package mirror and package provenance verification to reduce registry supply-chain exposure.
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 36)May include surrounding context.

Example: German holidays in 2025

bash
curl -s -X POST https://gateway.pipeworx.io/holidays/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_holidays","arguments":{"country":"DE","year":2025}}}'