Brand Video Maker Skill

• Outcome: Pass
• Latest audit: Sep 15, 2026 · 1:41 AM UTC
• Version: 1.0.2

Overview

This skill is a plain Markdown guide for AI-assisted brand replacement in videos, with no bundled code or hidden execution behavior found.

Before installing, prefer a pinned or verified ClawHub installer path if available, avoid running install commands with elevated privileges, and provide only the video and brand assets needed for the editing task.

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:6

Finding

Unpinned npm Package Execution Through npx

Content

View full analysis

Vulnerability Details

File Location: README.md:6-8
Vulnerability Type: Supply-chain risk from an unpinned executable dependency
Risk Level: Medium

Vulnerable Code

bash

npx clawhub install brand-video-maker

Technical Analysis

The documented installation command invokes clawhub through npx without specifying an exact package version, package integrity hash, trusted registry, or verified publisher. If the package is not already available locally, npx may retrieve it from the configured npm registry and execute it immediately.

The command therefore delegates code execution to a mutable third-party package whose contents can change after this project has been audited. A compromised publisher account, malicious package release, registry compromise, or dependency-chain compromise could cause users following the documented installation procedure to execute attacker-controlled code.

The repository provides no lockfile, checksum, vendored implementation, or other mechanism by which users can verify that the retrieved package is the version reviewed and intended by the project authors.

Attack Path

1. An attacker compromises the clawhub npm package, its publisher account, or a dependency included in a subsequently published release.
2. The attacker publishes a modified package version containing malicious installation or runtime behavior.
3. A user follows the installation instructions and runs npx clawhub install brand-video-maker.
4. npx resolves and downloads the mutable package from the user's configured registry.
5. The malicious package executes with the privileges of the user who invoked the command.
6. Subject to those privileges and the execution environment, the payload can access files, environment variables, credentials, and network resources available to that user.

Impact Assessment

Successful exploitation would permit arbitrary code execution under the invoki ...[truncated 665 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin clawhub to an exact, reviewed version rather than allowing mutable resolution, for example:

   bash

   npx --yes clawhub@<audited-exact-version> install brand-video-maker
   

2. Document the expected npm registry and verified package publisher so users can validate package provenance.
3. Publish and document a trusted integrity checksum or signed release artifact for the installer.
4. Prefer installing from a lockfile-controlled project dependency and invoking the pinned local binary instead of downloading and executing a package ad hoc.
5. Enable package provenance or signature verification in the release process and protect publisher accounts with strong multi-factor authentication.
6. Audit the pinned package and its transitive dependencies before recommending execution.
7. Advise users to run installation with least privilege in an isolated environment and never with elevated administrator or root permissions.

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 (1)

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 92% confidence

Finding

The README instructs users to run npx clawhub install brand-video-maker without pinning a specific package version, which can cause execution of whatever version is current at install time. If the referenced package or one of its delivery paths is compromised, users may unknowingly run malicious code during installation, and README install commands are commonly copy-pasted without scrutiny.

Content

No source excerpt is available for this finding.