Security audit

Trading Research

Security checks across malware telemetry and agentic risk

Overview

The runnable tools appear read-only, but the skill includes live Binance trading and account-access examples that need careful review before use.

Install only if you want a Binance-focused crypto research helper and are comfortable with it contacting Binance public market APIs. Do not provide live Binance API keys or use the bundled order-placement examples without separate review, testnet or dry-run safeguards, least-privilege keys, and explicit human confirmation. Treat trading outputs as informational, not personalized financial advice, and do not use the VPN suggestion to bypass regional restrictions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill instructs the agent to use local reference files and make external Binance API requests, but no permissions are explicitly declared. This creates a governance and consent gap: the runtime may allow file reads and network access without users or reviewers clearly understanding the skill’s capabilities.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The manifest description uses very broad trigger language such as 'any trading research questions about Bitcoin, altcoins, or crypto markets,' which can cause over-activation. Overly broad activation increases the chance the skill is invoked in contexts where network calls, file reads, or financial guidance are unnecessary or inappropriate.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The usage section enumerates wide activation conditions without clear exclusions or routing constraints, effectively encouraging invocation for a large class of crypto-related requests. In a financial-analysis skill with network-backed tooling, this broad scope raises the risk of unnecessary data access, accidental tool use, and inappropriate reliance on the skill for generalized advice.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: This reference includes live trading and cancellation endpoints with concrete request formats but does not clearly warn that these actions affect real funds and positions on production accounts. In a trading-research skill, that omission increases the chance an agent or user copies examples into live execution paths without recognizing the financial consequences.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The Python sample demonstrates authenticated account access and live order submission using API keys and secret-based signing, but it lacks an explicit warning about credential sensitivity and real-money execution. In this skill context, such copyable code can normalize handling secrets and submitting production orders, increasing the risk of credential misuse, accidental trading, and unauthorized account actions.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The document gives explicit buy/sell-style trading signals such as golden/death crosses without any accompanying warning that technical indicators are probabilistic, can fail, and may lead to financial loss. In a trading-research skill, users may reasonably treat this as actionable guidance, increasing the chance of unsafe reliance on the content.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The content recommends concrete trading actions related to position sizing, stop-loss placement, and breakout confirmation, but does not clearly warn about capital loss, slippage, leverage risk, or false signals. Because this skill is specifically about crypto trading research, omission of risk warnings makes the advice more likely to be followed as operational guidance.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: This file provides detailed, prescriptive trading strategies, position sizing formulas, entry/exit rules, and risk management guidance without a prominent disclaimer that the material is informational only and not financial advice. In the context of a trading-research skill that may be used by inexperienced users, this can encourage users to treat the content as actionable investment advice and suffer financial losses, especially in volatile crypto markets.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.