Back to skill

Security audit

OpenClaw MCP Debugger

Security checks for vulnerabilities and agentic risk

Overview

The skill is a plausible MCP debugging tool, but it asks users to run broad automatic repair actions that can restart local services without enough scoping or confirmation detail.

Install only if you are comfortable with a debugger that may perform broad automatic repair actions against local MCP services. Prefer running it first in a limited environment, avoid `--all` unless you understand the affected servers, and pin or preinstall a trusted OpenClaw CLI version before using the documented command.

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:20
Finding
Unpinned Third-Party Package Execution Through npx## Vulnerability Details **File Location**: `SKILL.md`, lines 20-23 **Vulnerability Type**: Unpinned and unverified third-party dependency execution **Risk Level**: High ```bash ## Usage ```bash npx openclaw skill run openclaw-mcp-debugger --all ``` ``` ### Technical Analysis The documented usage command invokes the `openclaw` npm package through `npx` without specifying an exact version, integrity hash, lockfile, trusted source, or expected publisher identity. If the package is not already installed locally, `npx` may resolve, download, and execute package code from the configured npm registry. Consequently, the code executed by users can change after this skill has been reviewed. A compromised publisher account, malicious package release, registry compromise, or unexpected upstream change could cause arbitrary code to run under the invoking user's account. The repository contains no implementation that would allow auditors to verify the advertised diagnostics and repair behavior independently. The undocumented `--all` argument may also broaden the command's operational scope, but its exact effects cannot be established from the repository contents. ### Attack Path 1. An attacker compromises the upstream `openclaw` package, its publisher account, or its distribution channel and publishes a malicious version. 2. A user follows the command in `SKILL.md` without pinning a previously audited version. 3. `npx` resolves the current package version from the configured npm registry and downloads it if necessary. 4. The package's lifecycle scripts or executable entry point run with the privileges of the invoking user. 5. Malicious package code can access resources available to that user, subject to operating-system and environment restrictions. ### Impact Assessment Successful exploitation could provide arbitrary code execution with the invoking user's privileges. Potential exposure includes user-readable files, environ ...[truncated 438 chars]
Remediation
## Remediation Suggestions 1. Pin `openclaw` to an exact, reviewed version rather than allowing `npx` to resolve the latest release. 2. Commit an appropriate lockfile and verify package integrity through supported hashes, signatures, and registry provenance metadata. 3. Document the expected package publisher, registry source, audited version, and exact behavior of the `--all` option. 4. Prefer checked-in, reviewable local implementation code over dynamically retrieving executable package content at invocation time. 5. Disable or explicitly control npm lifecycle scripts where operationally possible. 6. Run the command in a least-privileged, isolated environment with restricted filesystem, credential, and network access. 7. Establish a dependency update process that requires source review and security validation before changing the pinned version.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises an 'Auto-Fixer' that automatically restarts crashed MCP servers and repair paths for local services, but it does not warn that it may modify or interrupt running local infrastructure. In the context of agent-tool integrations, silently restarting services can cause data loss, disrupt workflows, alter system state, or mask deeper compromise, especially when the affected servers include custom adapters or local databases.

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding
The skill instructs users to execute `npx openclaw` without pinning a specific package version, which makes the executed code depend on whatever version is currently published or resolved at runtime. In a security-sensitive agent tooling context, this creates a supply-chain risk: a compromised upstream release or unexpected breaking change could execute arbitrary code on the user's machine.

Static analysis

No suspicious patterns detected.