ClawHub
Back to skill

Security audit

Sora Video

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed OpenAI Sora video-generation CLI with normal setup, billing, file, and API-key risks for that purpose.

Install only if you are comfortable using your own OpenAI API key for billable Sora operations. Prefer installing uv through a trusted package manager or by reviewing/verifying the installer first, avoid uploading confidential media unless allowed by your policy, monitor API spending, and confirm video IDs before using delete.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill advertises and relies on capabilities including environment variable access, filesystem interaction, and network access, yet declares no permissions. This creates a transparency and trust problem: an agent or platform may execute the skill with broader capabilities than a reviewer or user expects, increasing the chance of unintended secret exposure, local file access, or outbound data transfer.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The delete command performs an irreversible remote API deletion immediately when invoked, with no confirmation prompt, dry-run safeguard, or extra validation. In a CLI/agent context, mistaken arguments, automation errors, or prompt-induced misuse could destroy user assets or job history with little friction.

External Script Fetching

Low
Category
Supply Chain
Content
The CLI requires Python 3.10+ and uses `uv` for dependency management (auto-installs the `openai` SDK):
```bash
# Install uv if not present
curl -LsSf https://astral.sh/uv/install.sh | sh
```

## Pricing Guide
Confidence
90% confidence
Finding
The documentation instructs users to fetch and execute a remote install script via curl piped directly to a shell. If the upstream host, transport path, or script content is compromised, arbitrary code will run immediately on the user's machine with the user's privileges.

Chaining Abuse

High
Category
Tool Misuse
Content
The CLI requires Python 3.10+ and uses `uv` for dependency management (auto-installs the `openai` SDK):
```bash
# Install uv if not present
curl -LsSf https://astral.sh/uv/install.sh | sh
```

## Pricing Guide
Confidence
97% confidence
Finding
The explicit command chaining of a network fetch into `sh` is a classic high-risk execution pattern because it turns remote content into immediate code execution without review. In this skill's context, users are already being guided to set API credentials locally, so combining that environment with arbitrary shell execution raises the risk of credential theft, malware installation, or broader workstation compromise.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.