ClawHub
Back to skill

Security audit

Tomoviee Image to Video

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Tomoviee/Wondershare image-to-video API helper, with expected external API calls and credential handling that users should manage carefully.

Install only if you are comfortable sending image URLs, prompts, and any optional callback data to Tomoviee/Wondershare. Keep app_key and app_secret out of shared terminals, shell history, and CI logs, treat printed Basic tokens as secrets, and use callback URLs only for endpoints you control.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly performs outbound network calls to `openapi.wondershare.cc`, but the metadata shown does not declare corresponding network permissions. Undeclared network capability weakens platform transparency and review controls, and can cause users or orchestrators to invoke a skill without understanding that external data transmission will occur.

Intent-Code Divergence

Medium
Confidence
87% confidence
Finding
The skill is specifically described as an image-to-video integration, but this prompt guide documents and demonstrates a broad set of unrelated Tomoviee APIs including image, audio, soundtrack, and chaining workflows. In agent settings, overly broad reference material can expand the model’s perceived tool surface, causing it to generate instructions or workflows for capabilities the skill does not actually expose, which can lead to unauthorized use patterns, policy bypass through capability confusion, or accidental misuse of adjacent APIs.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description says the skill generates videos from an image and prompt via an external API, but it does not prominently warn that user-provided image URLs, prompts, and optional callback data are transmitted to a third-party service. This creates a privacy and data-handling risk, especially if users provide sensitive images, internal URLs, or confidential prompt content under the assumption processing is local.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script prints a credential-bearing Basic authentication token directly to stdout, which can expose secrets through terminal history, shell logging, CI logs, screen recordings, or shared consoles. Because the token is a reversible Base64 encoding of app_key:app_secret rather than a scoped temporary token, disclosure reveals the underlying credentials themselves.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.