Creator Intel V5

• Outcome: Review
• Latest audit: May 28, 2026, 12:10 PM
• Version:
  1.0.0

Overview

This is a coherent tech-news aggregator, but it ships with and uses a hardcoded Tavily API key and has mismatched run instructions that users should review before installing.

Review before installing. Ask the publisher to remove and rotate the embedded Tavily key, load credentials from user-controlled configuration, correct the script name in the run and cron instructions, and either enforce or accurately document history retention. Do not enable the Feishu cron job until you have verified the exact command and know how to disable it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill documents code execution that reads and writes local files and performs network requests, but it does not declare any permissions or capability boundaries. This creates a trust gap: operators may approve or invoke the skill believing it is metadata-only content generation, while it can access persistent local state and exfiltrate data over the network.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 96% confidence
• Finding: The declared purpose presents the skill as a technical-intel aggregator, but the documented behavior also includes persistent local history storage and external API use with a configured key. Undisclosed persistence and third-party transmission materially change the privacy and security profile, especially if queried content, URLs, or user-derived prompts are retained across runs or sent to external services.

Context-Inappropriate Capability

Medium

• Confidence: 99% confidence
• Finding: The script contains a hard-coded Tavily API key directly in source code, which is a real secret-exposure issue. Any user with access to the skill can extract and abuse the credential for unauthorized API usage, cost incurrence, quota exhaustion, or account compromise of the associated Tavily project.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: The hard-coded API credential is not only stored in code but also sent in outbound requests, meaning the skill actively uses an embedded secret without user disclosure. This increases risk because anyone reusing or inspecting the script can silently consume the credential, causing unauthorized external calls, billing exposure, and operational abuse.

VirusTotal

64/64 vendors flagged this skill as clean.