AI 价格计算器

Security checks across malware telemetry and agentic risk

Overview

This is a local AI pricing calculator with user-directed model-switching advice, not evidence of hidden or harmful behavior.

Safe to use for local cost comparisons. Before following the model-switching instructions, confirm you want future OpenClaw sessions to use that provider, understand the provider's pricing and data handling, and review the separate installer skill before installing it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Context-Inappropriate Capability

Medium
Confidence
84% confidence
Finding
These sections tell users to modify OpenClaw configuration files and environment variables even though the skill is framed as a pricing/recommendation tool. Documentation that drives users to change execution settings can alter provider selection, billing, and data-routing behavior, so the risk comes from undocumented scope expansion and the possibility of steering users into unintended configuration changes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal