Back to skill

Security audit

Pipeworx gamedeals

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but its MCP setup tells users to run an unpinned npm package with automatic approval, which creates avoidable local execution risk.

Review this before installing. The game-deals API behavior appears legitimate, but use a pinned, reviewed version of `mcp-remote` instead of `@latest` and avoid automatic `-y` execution where possible. Install only if you trust the Pipeworx endpoint and the npm package bridge running under your 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:44
Finding

Unpinned npm Package Is Automatically Downloaded and Executed

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 44-49
Vulnerability Type: Supply-chain risk caused by an unpinned executable dependency
Risk Level: High

Vulnerable Code

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

Technical Analysis

The MCP configuration invokes npx with both the automatic-confirmation option (-y) and the mutable package version mcp-remote@latest. When this configuration is used, npm can download and execute whichever package release the latest distribution tag references at that time.

Because the executable dependency is not pinned to a reviewed version or integrity hash, its effective code can change after the Skill has been audited. Automatic confirmation further removes an opportunity for the user to inspect or reject the package before execution. This creates a third-party supply-chain exposure: compromise of the package, its maintainer account, or its publication pipeline could result in arbitrary attacker-controlled code being executed locally.

Attack Path

  1. An attacker compromises the mcp-remote package, a maintainer account, or its release pipeline.
  2. The attacker publishes a malicious release and causes the npm latest tag to reference it.
  3. A user applies the MCP configuration documented in SKILL.md.
  4. npx -y mcp-remote@latest resolves and downloads the attacker-controlled release without interactive approval.
  5. The malicious package executes with the privileges and environment of the user running the Agent or MCP client.

Impact Assessment

Successful exploitation could permit arbitrary code execution under the Agent user's operating-system account. Depending on that account's permissions and environment, an attacker could access local files, environment variables, Agent-accessible credentials, and network resources; modify user-owne ...[truncated 294 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with an exact, reviewed package version, such as mcp-remote@X.Y.Z.
  2. Remove -y where practical so installation or execution requires explicit user confirmation.
  3. Lock and verify dependency integrity using a lockfile and registry-provided integrity hashes, or vendor a reviewed copy of the client.
  4. Establish a controlled update process in which new versions are reviewed and tested before the pinned version is changed.
  5. Run the MCP client with least privilege in an isolated environment, exposing only the files, credentials, and network destinations required for game-deal queries.
  6. Restrict package installation to a trusted registry and monitor the selected package for ownership changes, unexpected releases, and security advisories.
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 37)May include surrounding context.

Example: deals under $5 sorted by savings

bash
curl -s -X POST https://gateway.pipeworx.io/gamedeals/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_deals","arguments":{"upperPrice":5,"sortBy":"Savings","limit":5}}}'