Tomoviee Text to Video

• Outcome: Pass
• Latest audit: May 29, 2026 · 8:15 PM UTC
• Version: 1.0.6

Overview

This is a disclosed Tomoviee/Wondershare text-to-video API helper with normal third-party API and credential-handling cautions, but no evidence of hidden or destructive behavior.

Install only if you intend to use Tomoviee/Wondershare OpenAPI. Use a dedicated API key, avoid sensitive prompts and internal callback URLs, do not share terminal output containing generated Basic tokens, and monitor provider quota or billing when generating videos.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill clearly performs outbound network operations to an external API gateway, but the metadata does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: users and hosting platforms may not realize the skill transmits prompts and related parameters off-platform, weakening consent and security review.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill description and usage guidance do not warn users that prompt text and optional callback URLs are sent to a third-party service. Users may include sensitive, proprietary, or personal data in prompts without understanding that it will be transmitted externally, and callback URLs can expose internal endpoints or tokens if misused.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The documentation explicitly encourages use of callback URLs and publicly accessible media URLs but does not warn that prompts, media references, task metadata, and generated results may be sent to external third-party infrastructure. In a skill that processes user-provided creative content, this can lead to unintended disclosure of sensitive user data or internal URLs if operators or downstream agents assume these fields are local-only or privacy-neutral.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The script accepts secrets via command-line arguments and prints a credential-derived Basic auth token directly to stdout. Command-line arguments can be exposed through shell history and process listings, and stdout may be captured in logs or terminal scrollback, increasing the risk of credential leakage.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: Passing app_key and app_secret via command-line arguments can expose secrets to local users, process listing tools, shell history, audit logs, and crash reporting systems. This is especially risky on shared hosts, CI runners, or managed environments where command lines are routinely captured.

Credential Access

High

• Category: Privilege Escalation

Content

app_secret = sys.argv[2]
    
    token = generate_access_token(app_key, app_secret)
    print(f"Access Token: {token}")
    print(f"\nUse in Authorization header as: Basic {token}")

• Confidence: 93% confidence
• Finding: Access Token

VirusTotal

66/66 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.