ClawHub
Back to skill

Security audit

TA Radar

Security checks across malware telemetry and agentic risk

Overview

This crypto analysis skill has purpose-aligned local script execution and disclosed market-data network calls, with no evidence of credential theft, persistence, or destructive behavior.

Install only from a source you trust and review the current SKILL.md before use, especially because the embedded script is incomplete in this artifact. Expect your queried symbols or contract addresses to be visible to the listed public market-data services and proxy. Do not treat the generated report as financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to create a file in /tmp, execute Python, and delete the file, which expands behavior from simple analysis into general shell/code execution. Even though the embedded script appears aimed at technical analysis, this execution pattern increases attack surface because a modified skill or truncated/hidden payload could cause arbitrary command execution or unsafe filesystem interaction.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill sends user-supplied symbols or contract addresses to third-party services but does not clearly warn users that their inputs will be transmitted externally. This is dangerous because contract addresses and asset interests can be sensitive, and users may not expect exposure to Binance, Gate.io, DexScreener, and a public proxy.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The deployment guide instructs operators to forward the user's raw query directly to a hosted API endpoint, but it does not warn that free-form user input may contain sensitive data or describe retention, logging, or third-party exposure. In this skill context, users may paste wallet addresses, trading intentions, or other identifying text, so silently transmitting raw input to a deployed service creates a real privacy and data-handling risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal