Ora决策人开发专家

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed company/contact lookup tool that sends user-entered business identifiers to a fixed external API and stores returned results locally.

Before installing, understand that company names, domains, or LinkedIn company identifiers you search will be sent to Topeasy's external API using TPAgent.key if present. Avoid using it for confidential prospect lists unless that service is approved for your organization, and handle the generated JSON result files as potentially sensitive contact data.

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
95% confidence
Finding
The skill sends user-supplied company and contact lookup queries to an external service and relies on a locally stored API key, but it does not prominently warn users about this data flow. That omission can lead to unintentional disclosure of sensitive prospecting targets, search terms, or credential usage without informed consent.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script sends a user-supplied domain to a third-party API endpoint, which is a real data-disclosure concern because the user is not explicitly warned at runtime that their input will be transmitted off-host. In this skill’s context, external transmission is core functionality, but domains may still be sensitive business intelligence or customer targeting data, so the lack of clear disclosure and consent increases privacy and compliance risk rather than indicating malicious behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal