Back to skill

Security audit

Pipeworx dadjokes

Security checks for vulnerabilities and agentic risk

Overview

This dad-joke skill is straightforward, but its setup runs an unpinned npm helper from the internet, so users should review it before installing.

Install only if you are comfortable running a remote MCP bridge through npm. Prefer pinning mcp-remote to a reviewed exact version, running it with least privilege, and avoiding sensitive environment variables in the process environment.

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

Error
Location
SKILL.md:50
Finding

Unpinned npm Package Is Automatically Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 50–56
Vulnerability Type: Unpinned executable dependency and supply-chain exposure
Risk Level: High

Vulnerable Code

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

Technical Analysis

The setup invokes npx with both the automatic-confirmation option (-y) and the mutable dependency specifier mcp-remote@latest. Consequently, the command may download and execute whichever package release the npm registry identifies as the latest at installation or invocation time.

The executed package is not constrained to the version that was available during this audit. Changes made by the package publisher, compromise of the publisher or npm account, or a malicious supply-chain release could therefore introduce arbitrary executable code after the Skill has already been reviewed.

No evidence establishes that the current mcp-remote package is malicious. The vulnerability is the configuration's automatic execution of an unpinned, externally controlled dependency without a reviewed lockfile or integrity constraint.

Attack Path

  1. An attacker compromises the dependency publisher, its npm account, its build or release pipeline, or another relevant supply-chain component.
  2. The attacker publishes a malicious version that becomes the release resolved by mcp-remote@latest.
  3. A user applies the documented MCP configuration and starts the configured server.
  4. npx -y downloads the attacker-controlled package without requesting interactive confirmation.
  5. npm or npx executes the package, including any applicable package lifecycle behavior, with the privileges and environment of the Agent user.
  6. The malicious payload can access resources available to that user and perform arbitrary local actions.

Impact Assessment

Successful exploitation could prov ...[truncated 617 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with a reviewed, exact version, such as mcp-remote@x.y.z; do not use latest, caret ranges, tilde ranges, or other mutable selectors.
  2. Manage the dependency through a committed package manifest and lockfile rather than downloading it ad hoc for each invocation.
  3. Verify the resolved package using registry integrity metadata or a separately maintained cryptographic digest.
  4. Review the pinned package, its transitive dependencies, lifecycle scripts, and release provenance before deployment.
  5. Disable npm lifecycle scripts where operationally feasible, or install dependencies in a controlled build stage before runtime.
  6. Execute the MCP process under a dedicated, least-privileged account or sandbox with restricted filesystem, credential, environment-variable, and network access.
  7. Establish a controlled upgrade process in which dependency updates are reviewed, tested, and explicitly approved before changing the pinned version.
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 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    emoji: "😄"
    homepage: https://pipeworx.io/packs/dadjokes
---