Back to skill

Security audit

Sano Intel — 中国医疗产业情报引擎(探针资本出品)

Security checks across malware telemetry and agentic risk

Overview

This is a coherent healthcare data lookup skill, but it asks users to send an API token over unencrypted HTTP.

Use only if you trust the provider and are comfortable exposing queries and the API token to the network path. Prefer not to use valuable or reused tokens until the service offers HTTPS, and avoid storing the token permanently in shell startup files unless you understand the local exposure risk.

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

High
Confidence
99% confidence
Finding
The skill instructs users to send an API token in the X-API-Key header to an HTTP endpoint, not HTTPS. That exposes the credential and queried data to interception or modification by any network intermediary, especially on shared, enterprise, or public networks. The skill context makes this more dangerous because the token is required for all queries, so normal use repeatedly transmits the secret in cleartext.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The setup guidance tells users to persist the API token in ~/.zshrc without any warning about local credential exposure. Shell startup files are long-lived, may be backed up, shared across machines, exposed in support bundles, or accidentally committed, increasing the chance of token leakage. In this skill, that risk compounds with the separate use of insecure HTTP transport.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.