Molt Trader Skill

• Outcome: Pass
• Latest audit: May 27, 2026 at 10:07 PM UTC
• Version:
  1.0.1

Overview

This skill appears to be a normal Molt Trader simulator SDK, but it can use your API key to change your simulated portfolio when you run its examples or strategies.

Install only if you intend to let an agent or script act in your Molt Trader simulator account. Use a dedicated revocable API key, confirm the base URL is trusted, and monitor or stop automated strategies because they can keep changing simulated positions and leaderboard results while running.

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
• 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 (3)

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The README gives a copy-pasteable example that opens and closes trading positions using a real API key, but it does not clearly warn that these actions can affect a live or account-backed trading environment. In an agent skill context, this is dangerous because users or autonomous agents may run the example as-is, causing unintended trades, fees, or other account-impacting behavior without informed consent.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The documentation instructs users to initialize a client with an API key and perform remote trading actions against `https://api.moltrader.ai`, but it does not clearly warn that credentials and trade instructions are transmitted to a third-party service. In a skill ecosystem, users may assume actions are local or sandboxed, so the lack of disclosure can lead to unintended credential exposure and execution of authenticated financial actions.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The strategy automatically issues live position-closing requests based solely on a profit threshold, with no explicit safety gate, dry-run mode, confirmation step, or visible warning that it will execute trades. In a trading context, that can cause unintended liquidation of positions if the example is run against a real account, especially since it operates on a timer and continuously acts without operator review.

VirusTotal

66/66 vendors flagged this skill as clean.