Back to skill

Security audit

Ecommerce Video Ai Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only e-commerce video skill with a disclosed purpose and no bundled executable behavior, but its README uses an unpinned npx install command.

Review the install path before running it. Prefer a pinned, trusted clawhub version or an approved ClawHub installation workflow, and provide only the product images, listings, and campaign details needed for video generation.

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
README.md:5
Finding

Unpinned npm Package Download and Execution via npx

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 5-7
Vulnerability Type: Unpinned third-party dependency execution
Risk Level: Medium

bash
## Install
```bash
npx clawhub install ecommerce-video-ai
text

### Technical Analysis

The documented installation command invokes `clawhub` through `npx` without specifying a reviewed version or integrity constraint. If the package is not already available locally, `npx` can retrieve it from the configured npm registry and immediately execute its package entry point.

Consequently, the code executed by this instruction can change independently of the audited repository. The project contains no lockfile, integrity hash, vendored implementation, or other mechanism that binds the command to a specific reviewed release. The external package's implementation is also absent from the audited artifact, so its behavior could not be verified during this audit.

This is a supply-chain weakness rather than evidence that the current `clawhub` package is malicious.

### Attack Path

1. An attacker compromises the npm package, a maintainer account, the relevant package release process, or the user's configured package registry.
2. The attacker publishes or serves a malicious version of `clawhub`.
3. A user follows the installation instructions and runs `npx clawhub install ecommerce-video-ai`.
4. `npx` resolves and downloads the attacker-controlled package because the command does not identify a trusted version or integrity value.
5. The downloaded package executes with the permissions and environment of the invoking user.

### Impact Assessment

Successful exploitation could permit arbitrary code execution with the invoking user's privileges. Depending on that user's access and environment, the malicious package could read or modify user-accessible files, access environment variables and development credentials, alter installed project content, or make outbound networ
...[truncated 154 chars]
Remediation
View remediation

Remediation Suggestions

  • Pin clawhub to a specific release that has undergone security review, for example npx clawhub@<reviewed-version> install ecommerce-video-ai.
  • Verify the selected package version against an approved source and record its expected integrity metadata.
  • Prefer a lockfile-controlled installation workflow that separates dependency installation from execution.
  • Configure CI and deployment environments to use a trusted registry and immutable package versions.
  • Document the official package publisher and repository so users can validate package provenance.
  • Periodically review the pinned version before intentionally upgrading it, rather than implicitly executing the latest available release.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The README instructs users to run npx clawhub install ecommerce-video-ai without pinning a specific version of the package being executed. This creates a supply-chain risk because users may fetch and run whatever version is current at install time, including a maliciously published or compromised release, and npx commonly executes package code during installation or startup.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.