Back to skill

Security audit

Pipeworx deckofcards

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to do what it says, but its setup runs a mutable npm package automatically, which creates a local supply-chain risk users should review before installing.

Review this before installing. The card-deck behavior is coherent, but prefer a pinned, reviewed version of `mcp-remote`, run it with minimal environment access, and avoid exposing secrets or broad filesystem permissions to the MCP process.

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:55
Finding

Automatic Execution of an Unpinned npm Dependency

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 55–56
Vulnerability Type: T08: Insecure Dependencies
Risk Level: Medium

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

Technical Analysis

The MCP configuration invokes npx with the -y option to automatically download and execute mcp-remote@latest. The latest npm tag is mutable and does not identify a fixed, previously audited package version. The configuration also provides no package integrity hash or lockfile protection.

Consequently, the code executed by this configuration can change after the Skill has been reviewed. Automatic confirmation through -y further removes an opportunity for the user to inspect or reject a newly resolved package version. This creates a supply-chain exposure if the package, its maintainer account, or its publication process is compromised.

Attack Path

  1. An attacker compromises the mcp-remote npm package, a maintainer account, or the associated release process.
  2. The attacker publishes a malicious package version and causes the mutable latest tag to resolve to it.
  3. A user starts the MCP server using the configuration in SKILL.md.
  4. npx -y downloads the version currently referenced by latest without interactive confirmation.
  5. npx executes the malicious package locally.
  6. The payload runs with the permissions and environmental access of the user or Agent process that launched the MCP server.

Impact Assessment

Successful exploitation could result in arbitrary code execution under the privileges of the launching user. Depending on that user's permissions and runtime environment, a malicious dependency could access readable local files, environment variables, credentials, Agent-accessible resources, and network services. It could also modify files or execute additional commands within the user's authorization boundary.

The reviewed evidence does not es ...[truncated 199 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace mcp-remote@latest with an exact, reviewed version, such as mcp-remote@x.y.z.
  2. Install dependencies during a controlled deployment step rather than downloading them automatically whenever the MCP server starts.
  3. Use a lockfile and npm integrity metadata to verify the resolved package artifact.
  4. Remove -y where practical so unexpected installation or version-resolution changes require explicit approval.
  5. Monitor the pinned dependency for security advisories and upgrade only after reviewing and testing the target version.
  6. Run the MCP bridge with least privilege in an isolated environment, exposing only the files, credentials, and network destinations required for its stated function.
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.

bash
# Step 1: Create a deck
curl -s -X POST https://gateway.pipeworx.io/deckofcards/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"new_deck","arguments":{"count":1}}}'