Back to skill

Security audit

Mcporter 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

The skill is not deceptive, but it is a broad MCP control tool that can call arbitrary remote or stdio servers, run local commands, alter auth/config, start a daemon, and install an unpinned npm package.

Install only if you need a general-purpose MCP operator. Use trusted MCP endpoints, avoid sending secrets to untrusted servers, inspect any command used with --stdio, confirm before create/update/delete tool calls, and prefer a sandboxed or least-privileged environment with a reviewed pinned mcporter version where possible.

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:6
Finding

Unpinned npm Dependency Creates a Supply-Chain Execution Risk

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 6
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 skill declares installation of the npm package mcporter by package name without specifying an exact version, lockfile, or integrity hash. Consequently, the artifact installed during skill setup is determined by the package registry at installation time rather than by the reviewed skill contents.

npm packages can execute lifecycle scripts during installation and subsequently run with the permissions of the user operating the agent. If the package registry account, release pipeline, or upstream package is compromised, a malicious future version could execute code even though this skill file remains unchanged. The project contains no bundled implementation or dependency lockfile that would allow the installed code to be verified as part of this audit.

No evidence in the reviewed files establishes that the current upstream package is malicious. The finding concerns the unsafe, mutable dependency installation mechanism.

Attack Path

  1. An attacker compromises the upstream mcporter npm publisher account, package release process, or another component of its distribution chain.
  2. The attacker publishes a malicious version under the same package name.
  3. A system installs this skill's required binary using the unversioned package declaration.
  4. The package manager resolves the dependency to the attacker-controlled release.
  5. Malicious code executes through an npm installation lifecycle script or when the installed mcporter binary is invoked.
  6. The payload operates with the permissions and environmental access of the user or a ...[truncated 717 chars]
Remediation
View remediation

Remediation Suggestions

  • Pin mcporter to a specific, reviewed version rather than resolving an unspecified release.
  • Record and enforce the package's integrity digest through an appropriate lockfile or package-manager integrity mechanism.
  • Disable npm lifecycle scripts during installation where operationally feasible, and explicitly review any scripts before allowing them.
  • Retrieve packages only from an approved HTTPS registry with controlled configuration and provenance verification.
  • Verify package signatures or npm provenance attestations when available.
  • Scan the pinned package and its complete transitive dependency tree before deployment.
  • Prefer bundling or vendoring a reviewed artifact when reproducible package verification cannot be enforced.
  • Run installation and execution in a sandboxed, least-privileged environment without unnecessary secrets, filesystem access, or network permissions.
  • Establish an update process in which version changes require security review before the pinned dependency is advanced.
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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly advertises direct HTTP calls, stdio execution, authentication flows, and configuration edits, but provides no safety guidance about network egress, executing local commands, or modifying local state. In an agent-skill context, omission of these warnings can lead users or downstream agents to invoke side-effecting operations without understanding the security consequences.

Content

No source excerpt is available for this finding.

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
94% confidence
Finding

The remote URL example demonstrates calling an external MCP endpoint and passing a URL parameter, but does not disclose that request data may be sent to third-party services. This is risky in an agent setting because users may unknowingly expose sensitive prompts, tokens, or document contents to external systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The stdio example shows execution of a local command (bun run ./server.ts) without any warning that this launches arbitrary local code. In a skill consumed by an automated agent, this can normalize unsafe local process execution and increase the risk of running untrusted scripts or binaries.

Content

No source excerpt is available for this finding.