Tomoviee Image Redraw

• Outcome: Pass
• Latest audit: May 29, 2026, 8:15 PM
• Version:
  1.0.2

Overview

This skill is a straightforward Tomoviee/Wondershare image-redrawing API client, with privacy-sensitive third-party processing that users should understand before use.

Install only if you trust Tomoviee/Wondershare with the images and prompts you submit. Use a dedicated API key, avoid sensitive or regulated images unless approved, prefer short-lived public image URLs, do not pass internal/private URLs as image or callback parameters, and keep printed auth tokens out of logs and shared terminals.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence
• Finding: The skill clearly performs outbound network operations to a third-party API, but no corresponding permission declaration is present. This creates a transparency and governance gap: users or platform controls may not realize the skill can transmit data externally, increasing the risk of unintended data exfiltration or bypass of policy review.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The description and overview do not warn users that source images, masks, prompts, and optional callback URLs are transmitted to an external service at openapi.wondershare.cc. Because images and masks may contain sensitive or personal data, omission of this warning undermines informed consent and can lead to privacy exposure when users invoke the skill expecting local-only processing.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation instructs users to supply externally hosted image URLs and an optional callback URL, but it does not warn that those URLs cause user content and task metadata to be transmitted to third-party infrastructure. In an image-editing skill, this can expose sensitive images, masks, internal URLs, or callback endpoints and may lead to privacy, data residency, or SSRF-style risks if operators pass non-public resources.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The script prints the generated Basic authentication token directly to stdout, which can expose credentials through shell history, terminal logging, CI logs, screen recording, or shared consoles. Because the token is a reversible Base64 encoding of app_key:app_secret rather than a one-way derived token, disclosure directly reveals the underlying credentials.

VirusTotal

64/64 vendors flagged this skill as clean.