Bitagent Skill

Security checks across malware telemetry and agentic risk

Overview

The skill fits its BitAgent trading purpose, but it can use a wallet private key to make irreversible BSC token launches and trades without built-in confirmation safeguards.

Review carefully before installing. Use only a dedicated low-balance wallet, keep PRIVATE_KEY out of logs and shared configs, verify the source and npm dependencies, prefer testnet first, and require explicit user approval for every mainnet launch, buy, or sell.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill instructs the agent to execute a CLI that uses a wallet private key from environment variables and performs networked blockchain operations, yet it declares no permissions or safety boundaries. This creates a real capability/consent mismatch: an operator or higher-level system may treat the skill as low-risk while it can sign transactions, move funds, and interact with mainnet/testnet.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The README advertises token launch and trading operations but omits clear warnings that these actions can trigger real, irreversible blockchain transactions with financial consequences. In a skill specifically designed to buy, sell, and launch tokens, that omission increases the chance that users or agents invoke actions without understanding loss, slippage, or permanent fund transfer risk.

Missing User Warnings

High
Confidence
95% confidence
Finding
The README instructs users to place a wallet PRIVATE_KEY into configuration without emphasizing that this secret grants direct control over funds and must be handled as highly sensitive credential material. In a trading skill that can submit blockchain transactions, inadequate warning around private key handling materially raises the risk of wallet compromise and unauthorized transfers.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill enables launching tokens and buying/selling them on BSC using a configured private key, but it does not present an upfront warning about irreversible financial risk, live-fund exposure, or the consequences of returning transaction-driving CLI output. In this context, missing user warnings are especially dangerous because the skill is explicitly designed for high-risk, state-changing blockchain actions on mainnet/testnet.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The launch command can register and create a token on-chain immediately after parsing CLI arguments, including on mainnet, without any interactive confirmation, dry-run, or irreversible-action warning. In a skill specifically designed to launch tradable tokens, this increases the chance of accidental mainnet deployment, unintended fee expenditure, and irreversible creation of unwanted assets if the agent/user passes incorrect parameters.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The buy and sell paths execute live blockchain trades directly from command-line parameters with no confirmation prompt, no summary of token/amount/network, and only a hardcoded slippage setting. Because this skill is explicitly for trading tokens on BitAgent, an agent or user mistake can trigger unintended purchases or sales on mainnet, causing immediate and irreversible financial loss.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal