ClawHub
Back to skill

Security audit

Ad-Ready Pro

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it gathers ad assets and sends them to ComfyDeploy to generate advertising images.

Install only if you are comfortable sending product URLs, product images, logos, reference ads, and optional model/talent images to ComfyDeploy and possibly fetching assets from third-party sites. Use a scoped ComfyDeploy API key where possible, avoid unreleased or confidential campaign assets unless third-party processing is approved, and clean /tmp/ad-ready after auto-fetching sensitive images.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill directs the agent to use environment variables, write files under /tmp, access local paths, and make network requests, but it does not declare or constrain those capabilities. That creates a permission-transparency gap: an operator may invoke the skill without realizing it will fetch remote content, persist artifacts locally, and transmit data externally. In this context the behavior is expected for the feature, but the lack of explicit permission declaration still increases risk.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs automatic downloading of product images, brand logos, and reference ads from third-party websites and search results without requiring user confirmation or warning that these requests disclose browsing targets and may pull in untrusted content. Because the workflow encourages searching broadly online and saving results locally, it raises privacy, provenance, and compliance risks.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill sends product URLs, product images, logos, model images, and reference ads to ComfyDeploy, but it does not prominently warn the user that these assets will leave the local system and be processed by an external service. This is a genuine data-transmission issue because uploaded creative assets may be proprietary, licensed, or sensitive in a business context.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
When --auto-fetch is used, the script silently makes outbound requests to the user-supplied product URL and to third-party logo services, which can disclose the user's target URL, IP, user agent, and timing metadata without an explicit consent or disclosure step. In a URL-driven advertising skill, this behavior is expected functionally, but it still creates a privacy and network-boundary risk because user input can trigger access to arbitrary external hosts.

External Transmission

Medium
Category
Data Exfiltration
Content
## API Details

**Endpoint:** `https://api.comfydeploy.com/api/run/deployment/queue`
**Deployment ID:** `e37318e6-ef21-4aab-bc90-8fb29624cd15`

## ComfyDeploy Input Variables
Confidence
88% confidence
Finding
https://api.comfydeploy.com/

External Transmission

Medium
Category
Data Exfiltration
Content
sys.stderr.reconfigure(line_buffering=True)

DEPLOYMENT_ID = "e37318e6-ef21-4aab-bc90-8fb29624cd15"
API_BASE = "https://api.comfydeploy.com/api"

# Dynamic brand profiles from catalog
BRANDS_DIR = Path.home() / "clawd" / "ad-ready" / "configs" / "Brands"
Confidence
90% confidence
Finding
https://api.comfydeploy.com/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.