Back to skill

Security audit

Skill Scout

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed ClawHub skill-finder and installer; its main risks are ordinary community-skill and mutable CLI supply-chain risks, not hidden malicious behavior.

Install this only if you want an assistant to help manage OpenClaw skills from ClawHub. Before installing recommended community skills, inspect their source and requirements, prefer workspace installs, avoid bulk updates without review, and use a pinned or trusted local clawhub CLI instead of npx @latest when feasible.

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:61
Finding
Unpinned Runtime Package Execution via npx## Vulnerability Details **File Location**: `SKILL.md`, line 61 **Vulnerability Type**: `T08: Insecure Dependencies` **Risk Level**: Medium **Vulnerable Code**: ```bash npx clawhub@latest install <skill-slug> ``` ### Technical Analysis The documented installation command instructs the agent to retrieve and execute the mutable `latest` release of the `clawhub` npm package at runtime. Neither an exact package version nor a cryptographic integrity value is specified. Consequently, the code executed by this command may differ from the code available when the skill was audited. Because `npx` can download and execute npm package entry points, compromise of the package, its publishing account, or its dependency chain could result in arbitrary code execution under the identity running the agent. The command also installs a selected community skill, extending the supply-chain trust boundary further. The skill recommends inspection and warns that community skills are not audited, but these procedural safeguards do not provide reproducibility or integrity verification for the CLI package executed through `npx`. ### Attack Path 1. An attacker compromises the `clawhub` npm package, a maintainer account, or a transitive dependency and causes a malicious version to become the `latest` release. 2. A user asks the agent to install a skill. 3. The agent follows the documented command and executes `npx clawhub@latest install <skill-slug>`. 4. `npx` retrieves the mutable package release and executes its package entry point. 5. The malicious package runs with the permissions and environmental access of the agent process. 6. It may access available workspace data, environment variables, or user-accessible files and may install additional unsafe content. ### Impact Assessment Successful exploitation could provide arbitrary code execution with the privileges of the account running the agent. The affected scope may include the current workspace, user-readable or u ...[truncated 369 chars]
Remediation
## Remediation Suggestions - Replace `@latest` with an exact, reviewed package version, for example `npx clawhub@X.Y.Z`. - Prefer a trusted, preinstalled CLI managed through a lockfile or controlled package-management process. - Verify npm package provenance and cryptographic integrity before execution. - Review and pin relevant transitive dependencies where the packaging workflow permits it. - Require explicit user confirmation before downloading and executing a package or installing a community skill. - Preserve the existing inspection-first workflow, but treat source inspection and malware reports as supplementary controls rather than substitutes for version and integrity pinning. - Test upgrades in an isolated environment before changing the approved package version.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation triggers are broad phrases like 'find me a skill', 'add a tool for...', and 'I want to automate...', which can overlap with ordinary conversation and cause the skill to activate unexpectedly. In this context, unintended activation is more dangerous because the skill is designed to search for and recommend installation of external community-built skills, potentially steering users toward risky actions without an explicit opt-in.

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding
The command `npx clawhub@latest install <skill-slug>` executes the latest published package version at runtime, which creates a supply-chain risk if the package is compromised or a malicious version is published. Because this skill's purpose is to discover and install third-party skills, users may be encouraged to run this command frequently, increasing exposure to unreviewed code execution.

Static analysis

No suspicious patterns detected.