ClawHub

Video Ad

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Pexo video-ad helper that sends user-provided briefs and media to Pexo’s hosted service, with some credential-handling risks users should understand.

Install only if you are comfortable sending ad briefs, product details, and uploaded media to Pexo's hosted service. Keep ~/.pexo/config private, restrict its permissions, avoid putting secrets or regulated data in prompts or files, and remember that running generation can consume Pexo credits, although the scripts do not appear to purchase credits automatically.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script executes `source "$config_path"` on a user-controlled config file, which means any shell commands placed in that file will run with the privileges of whoever launches the diagnostic tool. A config file should be treated as data, not executable code; if an attacker can modify it or trick a user into using a malicious `PEXO_CONFIG` path, this becomes arbitrary code execution.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README explicitly says all creative work happens server-side and the skill delegates to a hosted backend, but it does not clearly warn users that their prompts, product briefs, images, and other campaign materials will be transmitted to Pexo. This creates a real privacy and data-handling risk because users may unknowingly send confidential marketing plans, unreleased product details, or sensitive media to a third-party service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to send the user's request verbatim and upload any provided files to a third-party service, but it does not require an explicit user-facing disclosure or consent step before transferring potentially sensitive data. This can cause unintended exfiltration of private text, images, audio, or other assets to Pexo, especially when users may not realize their materials leave the local environment.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The setup instructions direct users to store a long-lived API key in a plaintext file under their home directory without any warning about credential sensitivity or restricting file permissions. If the file is readable by other local users, included in backups, or accidentally exposed through logs, support bundles, or dotfile sync, the API key could be stolen and used to access the Pexo account and API.

Session Persistence

Medium
Category
Rogue Agent
Content
## Quick Start

### 1. Create config file

```bash
mkdir -p ~/.pexo
Confidence
90% confidence
Finding
Create config file ```bash mkdir -p ~/.pexo cat > ~/.pexo/config << 'EOF' PEXO_BASE_URL="https://pexo.ai" PEXO_API_KEY="sk-<your-api-key>" EOF ``` Get your API key at: https://pexo.ai - If you do n

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal