Back to skill

Security audit

Pipeworx numbersapi

Security checks for vulnerabilities and agentic risk

Overview

This NumbersAPI skill has a coherent purpose, but it should be reviewed because its setup runs an auto-approved, unpinned npm package locally.

Before installing, consider pinning mcp-remote to a reviewed exact version or running the MCP client in a restricted environment. The skill does not ask for credentials and appears limited to number facts, but the setup command can execute future npm package contents under your local user account.

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:23
Finding

Unpinned npm Dependency Is Automatically Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 23–24
Vulnerability Type: Unpinned executable dependency
Risk Level: High

Vulnerable Code

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

Technical Analysis

The configuration invokes npx with the mutable dependency reference mcp-remote@latest. The -y option automatically approves installation, so the package selected by the npm registry is downloaded and executed without interactive confirmation.

Because the latest tag can be changed after this Skill has been reviewed, the code executed at runtime is not necessarily the code that existed during the audit. No exact version, lockfile, or package integrity hash constrains the downloaded artifact. This creates a supply-chain risk if a future release is malicious or if the package maintainer account, package, or registry delivery process is compromised.

Attack Path

  1. An attacker compromises the npm package, its maintainer account, or the relevant package-distribution process.
  2. The attacker publishes a malicious release and assigns it to the mutable latest tag.
  3. A user starts the configured MCP server.
  4. The configuration runs npx -y mcp-remote@latest.
  5. npx automatically downloads and executes the attacker-controlled package without requesting confirmation.
  6. The malicious package runs locally under the account and environment used to start the Agent.

Impact Assessment

Successful exploitation could permit arbitrary code execution with the privileges of the Agent user. Depending on that account's permissions and environment, malicious package code could access readable local files, environment variables, Agent-accessible credentials, and network resources; alter user-owned files; or launch additional processes.

The finding does not establish that the current mcp-remote package is malicious. The risk arises because the documented config ...[truncated 118 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with an exact, reviewed version, such as mcp-remote@<audited-version>.
  2. Manage the dependency in a project manifest and lockfile rather than resolving it dynamically on every startup.
  3. Verify the package artifact using npm lockfile integrity metadata or an independently validated cryptographic checksum.
  4. Remove automatic approval through -y where operationally feasible so unexpected installation behavior is visible to the user.
  5. Review dependency updates before changing the pinned version, including package ownership, release provenance, dependency changes, and published artifact contents.
  6. Run the MCP client with least privilege in an isolated environment with restricted filesystem, credential, and network access.
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