Automated Video Generator

Security checks across malware telemetry and agentic risk

Overview

The video generator is mostly purpose-aligned, but it ships actual-looking API keys and exposes sensitive environment and command-running capabilities that need review before use.

Use caution before installing. The project purpose is coherent for a self-hosted video generator, but remove any bundled .env secrets, supply your own provider keys, confirm MCP env values are masked, and verify that command-running tools cannot execute arbitrary shell commands.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
Medium
What this means

An agent could trigger local commands that modify generated files, run renders, or otherwise affect the project environment.

Why it was flagged

The MCP pipeline command path executes a variable command through the shell. Running pipeline commands is purpose-aligned, but this is high-impact unless a strict whitelist and user approval are enforced.

Skill content
const child: ChildProcess = exec(cmd, { cwd: resolveProjectPath() }, (error, stdout, stderr) => {
Recommendation

Verify that only a small fixed set of safe pipeline commands can be run, avoid arbitrary shell strings, and require explicit user confirmation for cleanup, generation, or deletion actions.

#
ASI03: Identity and Privilege Abuse
High
What this means

The app may use leaked or shared provider credentials, and those keys could be abused or rate-limited by anyone who receives the artifact.

Why it was flagged

The packaged artifact contains actual-looking provider API credentials even though the registry declares no credentials or required environment variables.

Skill content
PEXELS_API_KEY=O23...; GEMINI_API_KEY=AIza...
Recommendation

Remove real secrets from the skill package, rotate the exposed keys, ship only .env.example placeholders, and declare required/optional credentials in metadata.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Installing or running the package executes local application code and dependencies on the user's machine.

Why it was flagged

The skill asks users to run an npm-hosted package, and the same document also promotes downloading a Windows .exe installer. This is expected for this kind of app, but users must trust the package and release source.

Skill content
claude mcp add automated-video-generator -- npx automated-video-generator
Recommendation

Install from the official repository/package only, prefer pinned versions where possible, and verify release provenance before running the Windows installer.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

An attached agent may be able to read or alter provider configuration that includes API keys or service settings.

Why it was flagged

The MCP interface exposes environment viewing and editing. Because this project stores API keys in .env, these tools are sensitive unless values are masked and changes are explicitly approved.

Skill content
"read_env_config", "description": "View environment settings." ... "update_env_config", "description": "Change environment settings."
Recommendation

Mask secret values in MCP responses, require explicit user approval before updating env configuration, and avoid exposing full .env contents to agent context.