ClawHub

Ora地图拓客专家

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it queries a map-search service for business leads and saves the returned listings locally for the agent to summarize.

Install only if you are comfortable sending search keywords, city coordinates, and any TPAgent.key present in the skill directory hierarchy to the configured third-party map-search API. Expect raw business contact data to be saved locally as JSON and shown to the agent for summarization.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill directs the agent to execute a Node.js script that performs a map search API call and returns raw data, but it declares no corresponding permissions or user-facing capability disclosure. This creates a transparency and policy-enforcement gap: users and hosting systems may not realize the skill can perform network-backed data collection and file-based output handling.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs the agent to read a raw JSON data file produced by the script and present its contents, but it does not warn users that raw harvested business data may be exposed verbatim. This can leak unexpected sensitive or regulated information present in the file, especially if the upstream script returns more fields than the user expects.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal