Back to skill

Security audit

Mcporter

Security checks for vulnerabilities and agentic risk

Overview

The skill is a small, disclosed mcporter command guide, but it enables broad MCP calls, local stdio commands, auth/config changes, daemon use, and an unpinned npm install that users should handle carefully.

Install this only if you intend to let the agent use mcporter. Treat MCP URLs, stdio server commands, auth/config changes, and daemon commands as sensitive: use trusted endpoints, avoid passing secrets unless needed, review local commands before running them, and prefer a pinned or otherwise controlled mcporter package version.

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:5
Finding

Unpinned Third-Party Node.js Dependency

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 5
Vulnerability Type: Unpinned third-party package installation
Risk Level: Medium

Vulnerable Code:

yaml
metadata: {"clawdbot":{"emoji":"📦","requires":{"bins":["mcporter"]},"install":[{"id":"node","kind":"node","package":"mcporter","bins":["mcporter"],"label":"Install mcporter (node)"}]}}

Technical Analysis

The installation metadata requests the mcporter Node.js registry package without specifying an exact version or package integrity hash. Consequently, the package content installed in the future may differ from the content reviewed when this Skill was published.

This creates a supply-chain risk because package resolution depends on mutable external registry state. If the package publisher account, registry entry, or transitive dependency chain is compromised, a malicious release could be selected during installation. Node.js packages may execute lifecycle scripts during installation, allowing compromised package content to run commands on the host.

Attack Path

  1. An attacker compromises the mcporter package publisher, its registry account, or a dependency in its supply chain.
  2. The attacker publishes a malicious version that contains harmful runtime behavior or an installation lifecycle script.
  3. A user installs the Skill dependency using the unversioned package declaration.
  4. The package manager resolves the attacker-controlled release because no exact reviewed version or integrity constraint is enforced.
  5. Malicious package code executes during installation or when the mcporter command is invoked.

Impact Assessment

Successful exploitation could execute arbitrary code with the privileges of the account performing the installation or running mcporter. Depending on those privileges, the attacker could access local files and credentials available to that account, alter project or user configuration, invoke network ...[truncated 170 chars]

Remediation
View remediation

Remediation Suggestions

  • Pin mcporter to an exact, reviewed version rather than allowing unconstrained registry resolution.
  • Enforce package integrity verification using a trusted lockfile or a cryptographic integrity hash.
  • Obtain the package only from an explicitly trusted registry and protect registry configuration from dependency-confusion attacks.
  • Review direct and transitive dependencies before updating the pinned version.
  • Disable package lifecycle scripts during installation where operationally feasible, or perform installation in an isolated environment.
  • Run the installed CLI with least privilege and restrict its filesystem, credential, and network access.
  • Establish a controlled update process in which new versions are reviewed and tested before the version pin and integrity data are changed.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 20)May include surrounding context.

md
Call tools
- Selector: `mcporter call linear.list_issues team=ENG limit:5`
- Function syntax: `mcporter call "linear.create_issue(title: \"Bug\")"`
- Full URL: `mcporter call https://api.example.com/mcp.fetch url:https://example.com`
- Stdio: `mcporter call --stdio "bun run ./server.ts" scrape url=https://example.com`
- JSON payload: `mcporter call <server.tool> --args '{"limit":5}'`

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill encourages calling arbitrary remote MCP endpoints by URL and executing ad-hoc stdio commands such as bun run ./server.ts, but does not warn that these actions can contact untrusted services or launch local processes. In an agent setting, this increases the risk of SSRF-like outbound access, exfiltration, or execution of attacker-controlled local command lines.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly exposes auth and config operations, including add/remove/import/login/logout, but provides no warning that these commands can modify local configuration or alter authentication state. In an agent context, that omission can lead users or higher-level orchestrators to invoke state-changing commands without understanding the persistence and security implications.

Content

No source excerpt is available for this finding.