Back to skill

Security audit

Pipeworx dogsapi

Security checks for vulnerabilities and agentic risk

Overview

This dog-breed lookup skill is mostly coherent, but its MCP setup tells users to auto-download and run an unpinned npm package.

Review the MCP setup before installing. Prefer a pinned, reviewed `mcp-remote` version or use the direct curl/API endpoint in a restricted environment. Do not run the MCP bridge with access to sensitive files or environment variables unless you trust the npm package and service operator.

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:40
Finding

Unpinned npm Package Is Automatically Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 40–46
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

The documented MCP configuration invokes npx with automatic confirmation and the mutable latest package tag:

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

Technical Analysis

The command uses npx -y to download and execute mcp-remote@latest without prompting the user and without pinning an audited version. Because the latest tag can resolve to a different package release after the Skill has been reviewed, the code ultimately executed is not immutable.

This creates a supply-chain exposure: compromise of the npm package, its publisher account, or its release process could cause a malicious future version to be downloaded and executed. The project contains no lockfile, integrity hash, or other mechanism that verifies the expected package artifact.

The documented curl example can call the fixed service endpoint directly, whereas the MCP configuration introduces a general-purpose third-party executable into the local environment.

Attack Path

  1. An attacker compromises the mcp-remote npm package, its maintainer account, or its publishing pipeline.
  2. The attacker publishes a malicious release and assigns it to the latest distribution tag.
  3. A user enables or launches the documented MCP configuration.
  4. npx -y mcp-remote@latest retrieves the attacker-controlled release without an interactive confirmation.
  5. The downloaded package executes with the permissions and environment of the user or agent process.
  6. The malicious package can attempt to access resources available to that process or execute further commands.

Impact Assessment

Successful exploitation could provide arbitrary code execution with the ...[truncated 636 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with an exact, reviewed version such as mcp-remote@X.Y.Z; do not use a mutable tag or version range.
  2. Record and verify the expected package integrity hash through an appropriate lockfile or controlled installation process.
  3. Avoid npx -y for first-time or unverified execution so package installation does not proceed without user confirmation.
  4. Prefer installing dependencies from a reviewed lockfile rather than downloading executable code dynamically whenever the Skill starts.
  5. Document the expected package publisher, version, and integrity value so users can validate the artifact.
  6. Run the MCP bridge in a restricted environment with only the filesystem, environment variables, and network access required for the dog-data service.
  7. Establish a controlled dependency-update process in which new 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 9)May include surrounding context.

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