Video Script Ai Skill

• Outcome: Pass
• Latest audit: Sep 15, 2026 · 1:42 AM UTC
• Version: 1.0.2

Overview

This is a content-writing skill for short video scripts, with no bundled executable code or hidden high-impact behavior found.

Before installing, prefer a version-pinned or otherwise verified ClawHub install path if available. The skill itself appears limited to generating short-video scripts, but users should still review generated marketing claims and platform-specific advice before publishing content.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: README.md:5

Finding

Unpinned npm Package Execution During Installation

Content

View full analysis

Vulnerability Details

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

Vulnerable Code

markdown

## Install
```bash
npx clawhub install short-video-script

text

### Technical Analysis

The installation instructions invoke `clawhub` through `npx` without specifying a reviewed package version or integrity value. If the package is not already available locally, `npx` may retrieve the currently published npm package and immediately execute it with the invoking user's permissions.

Because the resolved package version is mutable and its implementation is not included in this repository, the code ultimately executed by this command cannot be verified from the audited files. Compromise of the npm package, its dependencies, its publishing account, or the relevant package-resolution path could cause attacker-controlled code to run during installation.

No malicious payload was found in the audited project itself. The risk arises from the unpinned external installation dependency.

### Attack Path

1. An attacker compromises the `clawhub` npm package, one of its transitive dependencies, or an associated publishing account.
2. The attacker publishes a malicious package version that is eligible for resolution by the unversioned `npx clawhub` command.
3. A user follows the installation command documented in `README.md`.
4. `npx` retrieves and executes the attacker-controlled package version.
5. The malicious installation process runs with the permissions of the invoking user and can access resources available in that execution context.

### Impact Assessment

Successful exploitation could permit arbitrary code execution with the privileges of the user running the installation command. Depending on that user's environment, the executed package could read or modify local files, access environment variables and developer credentials, alter p
...[truncated 259 chars]

Remediation

View remediation

Remediation Suggestions

• Pin clawhub to a specific, reviewed version rather than relying on the latest resolvable release.
• Verify the package's official npm identity, provenance, maintainers, and release integrity before recommending execution.
• Use lockfiles and integrity metadata where the installation workflow supports them.
• Prefer a workflow that separates package download and inspection from execution.
• Document the expected official package registry and source repository to reduce dependency-confusion and package-spoofing risk.
• Periodically review the pinned release and its transitive dependencies before updating it.

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 90% confidence

Finding

The README instructs users to run npx clawhub install short-video-script without pinning a specific version of the package being executed. This creates a supply-chain risk because npx will resolve and run the latest published package, so a compromised, typosquatted, or maliciously updated package could execute arbitrary code on the user's machine during installation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The description includes Chinese text alongside English, which introduces a language expectation without stating whether multilingual output is optional or user-selected. Under the policy rule, language behavior should be opt-in or clearly justified when a specific locale is imposed or implied.

Content

No source excerpt is available for this finding.