保险产品解析

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward insurance product lookup that calls a disclosed external product-detail API, with minor transparency and reliability caveats.

Install only if you are comfortable with selected insurance product identifiers being sent to the external product-detail API. Confirm important insurance details against official policy documents, and verify that any missing product-mapping CSV comes from a trusted source if you need product-name matching.

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to call an external API via scripts/main.py but does not clearly warn the user that their query will trigger an outbound request. This can undermine informed consent and privacy expectations, especially if user-supplied product names or related context are transmitted to external services.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal