Agent Crypto Lens

Security checks across malware telemetry and agentic risk

Overview

The skill appears to use Gemini for crypto sentiment analysis in a purpose-aligned way, but users should avoid sending confidential financial research unless they trust that provider flow.

Install only if you are comfortable sending the relevant token names, news snippets, market data, prompts, and derived sentiment text to Google Gemini. Do not include private trading strategies, regulated data, secrets, or proprietary research unless that disclosure is acceptable under your policies.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill sends token names, news content, market data, and derived sentiment text to an external LLM provider, but this file contains no consent, minimization, or disclosure mechanism. If users supply proprietary research, private market intelligence, or regulated data, that content may be transmitted to third-party infrastructure unexpectedly.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: This code sends the combined system prompt and user message to Google's Gemini API, which can expose potentially sensitive user or business data to a third-party service. In an agent skill that analyzes crypto market data and sentiment, prompts may contain proprietary strategies, API-derived content, or user-supplied text, so lack of explicit disclosure and consent creates a real privacy and compliance risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal