Back to skill

Security audit

Pipeworx jikan

Security checks for vulnerabilities and agentic risk

Overview

The skill’s stated Jikan API purpose is coherent, but its connection instructions automatically run mutable third-party code on the user’s machine.

Review the connection command before installing. Prefer a pinned mcp-remote version or a managed lockfile, and run the MCP server with only the local and network access needed for Jikan lookups.

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:21
Finding

Unpinned Third-Party Package Is Downloaded and Executed Automatically

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 21–27
Vulnerability Type: Unpinned dependency execution through npx
Risk Level: Medium

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

Technical Analysis

The configuration invokes npx -y to download and execute mcp-remote@latest. The latest npm tag is mutable and does not identify an immutable, previously reviewed release. The -y option suppresses confirmation, allowing the resolved package and its dependency tree to execute automatically.

The project contains no exact version pin, package lockfile, integrity hash, or local implementation that would constrain the package to audited content. Consequently, the effective code executed by this skill can change after the skill itself has been reviewed.

This finding does not establish that the current mcp-remote package is malicious. It identifies a supply-chain execution path that could become exploitable if the package, a transitive dependency, its maintainer account, or the package registry distribution process were compromised.

Attack Path

  1. An attacker compromises the npm package, a maintainer account, or a dependency resolved by mcp-remote@latest.
  2. The attacker publishes a malicious version that becomes the package's latest release.
  3. A user installs or launches the MCP server using the documented configuration.
  4. npx -y retrieves the mutable latest release without an interactive confirmation step.
  5. Package lifecycle logic or runtime code executes under the invoking user's account.
  6. The malicious code can perform actions permitted to that account, including reading accessible local files, accessing environment variables, initiating network connections, or modifying user-writable data.

Impact Assessment

Successful exploit ...[truncated 418 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 version range or mutable distribution tag.
  2. Manage the package through a committed package manifest and lockfile so that both direct and transitive dependency versions are reproducible.
  3. Verify downloaded package integrity using the package manager's integrity metadata or an independently maintained checksum.
  4. Review the pinned package, its lifecycle scripts, and its transitive dependencies before deployment.
  5. Avoid automatic confirmation with npx -y for first-time or security-sensitive execution. Prefer an explicit installation and approval workflow.
  6. Run the MCP process with least privilege in an isolated environment, exposing only the files, environment variables, and network destinations required for the Jikan integration.
  7. Establish a controlled dependency-update process that includes security review and testing before changing the pinned version.
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