Back to skill

Security audit

system-info-windows-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward local system-information helper, with install-documentation cautions but no evidence of hidden, persistent, destructive, or exfiltrating behavior.

Install only if you are comfortable sharing basic local host details with the agent session. Prefer a pinned or otherwise verified ClawHub installer and confirm whether the intended skill name is system-info-skill or system-info before running the documented npx 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

Warning
Location
SKILL.md:13
Finding
Unpinned Package Execution in Installation Instructions## Vulnerability Details **File Location**: `SKILL.md:13-17` and `README.md:17-21` **Vulnerability Type**: Unpinned third-party package execution **Risk Level**: Medium **Vulnerable code in `SKILL.md`:** ```bash Install from ClawHub: ```bash npx clawhub install system-info-skill ``` ``` **Vulnerable code in `README.md`:** ```bash ## Installation ```bash npx clawhub install system-info ``` ``` ### Technical Analysis The documented installation process invokes `clawhub` through `npx` without specifying an exact package version or an integrity constraint. If the package is not already available locally, `npx` can retrieve and execute a package from the configured npm registry. Consequently, the code executed during installation may differ from the code that was reviewed. This creates a supply-chain exposure: compromise of the upstream package, registry account, package namespace, or a subsequently published version could cause users following the documentation to execute attacker-controlled package lifecycle scripts or command-line code. The documentation also uses inconsistent skill identifiers: `system-info-skill` in `SKILL.md` and `system-info` in `README.md`. Although this inconsistency does not itself prove malicious behavior, it makes package provenance harder to verify and may cause users to install an unintended artifact. ### Attack Path 1. An attacker compromises the upstream `clawhub` package or its publisher account, or gains control over the package name resolved by the user's registry. 2. The attacker publishes a malicious package version containing hostile lifecycle scripts or CLI behavior. 3. A user follows the documented `npx clawhub install ...` command. 4. `npx` resolves and downloads the unpinned package version from the configured registry. 5. The downloaded package executes with the privileges of the user running the installation command. 6. The malicious package can access files ...[truncated 854 chars]
Remediation
## Remediation Suggestions 1. Pin the installer to an explicitly reviewed version, for example: ```bash npx clawhub@<reviewed-version> install system-info-skill ``` 2. Prefer an installation process that verifies a cryptographic signature or published checksum before executing downloaded content. 3. Use a trusted, explicitly configured registry and document the expected package publisher and provenance. 4. Consider installing the reviewed CLI version separately with lifecycle scripts disabled where compatible, then invoking the locally verified executable. 5. Make the skill identifier consistent across `SKILL.md` and `README.md`. 6. Add release documentation identifying the exact installer version, skill version, package digest, and verification procedure. 7. Advise users not to run the installation command with administrative privileges unless strictly required.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Hidden Instructions

High
Category
Prompt Injection
Content
---
name: system-info-skill
description: Query system information including OS, CPU, memory, and disk usage. Use when users ask about system configuration, resource usage, performance diagnostics, or basic system info. Supports Windows, Linux, and macOS.
---
Confidence
60% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill documentation is written entirely in Chinese, including the feature descriptions and usage guidance, without indicating that other languages are supported or that the locale restriction is intentional. Under the policy, forcing a specific language without user opt-in or justification is a natural-language policy violation.

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding
The README instructs users to run `npx clawhub install system-info` without pinning an exact package version. This can cause users to execute whatever version is current at install time, increasing supply-chain risk if a malicious or compromised release is published under that package name.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation description is broad enough to match many ordinary support and diagnostics requests, which increases the chance this skill is invoked in situations where users did not specifically intend system inspection. Because the skill gathers host details like OS, CPU, memory, and disk usage, overbroad triggering can expose sensitive environment information unnecessarily or expand the agent's effective permissions surface.

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.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
This code embeds user-facing comments, console output, argument descriptions, and the program description entirely in Chinese. Because the file provides no opt-in, locale selection, or documented justification that the skill is intended only for Chinese-speaking users, it creates a natural-language locale policy issue.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The package description is written entirely in Chinese, which indicates a language-specific presentation without any accompanying note that the skill is intended only for Chinese-speaking users or that other languages are supported. Under the policy, forcing a specific language without opt-in or justification is a natural-language policy concern.

Static analysis

No suspicious patterns detected.