ClawHub
Back to skill

Security audit

Streme Token Launcher

Security checks across malware telemetry and agentic risk

Overview

This skill appears aligned with launching Streme tokens, but it can trigger real Base mainnet deployments using a wallet private key without strong warnings or confirmation safeguards.

Review carefully before installing or running. Use a dedicated low-balance wallet, verify the Base/Streme contract addresses and dependencies, set token parameters explicitly, use scoped image-hosting credentials, and require manual approval of the exact transaction before any deployment is submitted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill includes code and instructions that use environment variables and make network requests, but the metadata declares no permissions. This creates a transparency and governance gap: an agent or operator may invoke a skill that transmits data externally or relies on secrets without having clearly disclosed those capabilities.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger language is broad enough to activate on generic token deployment requests, which can cause the agent to route users into a real blockchain deployment workflow without sufficient confirmation. In a skill that can lead to irreversible on-chain actions, overly broad activation materially increases the chance of accidental use.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This skill describes deployment of real tokens on Base but does not prominently warn that actions may incur gas costs, create irreversible on-chain state, and potentially deploy economically significant assets. In this context, missing safety disclosure is especially risky because users may mistake the workflow for a simulation or underestimate the financial and reputational consequences.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/upload-image.ts:169