ClawHub
Back to skill

Security audit

Crypto Price Prediction

Security checks across malware telemetry and agentic risk

Overview

This skill is a small, disclosed crypto prediction API wrapper with no evidence of hidden data access, persistence, or destructive behavior.

Install this only if you are comfortable sending BTC/ETH prediction requests to the disclosed Zeabur API and trusting your local runtime configuration. Do not treat the output as financial advice, and avoid setting PYTHON_CMD unless you control and trust the interpreter path.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation describes outbound network access to an external API and likely environment usage (for timezone configuration), but no permissions are declared. This creates a transparency and policy-enforcement gap: users or orchestrators may treat the skill as lower risk than it is, while it can still exfiltrate data via network access or behave differently based on environment state.

Context-Inappropriate Capability

Medium
Confidence
87% confidence
Finding
The skill launches a local Python process and permits the executable path to be overridden through the PYTHON_CMD environment variable. In a plugin expected to simply fetch a prediction, this expands the trust boundary to local process execution; if an attacker can influence environment variables or deployment configuration, they can cause arbitrary code execution under the plugin's privileges.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
skill.js:43