门店销售业绩分析

Security checks across malware telemetry and agentic risk

Overview

This is a purpose-aligned retail sales analysis skill, with manageable risks around business data access and an unbundled local API client dependency.

Install only if you trust the local api_client used by your OpenClaw environment. Use a read-only, least-privileged account, and provide only the store IDs, clerk IDs, and date ranges the agent is allowed to analyze.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases are broad enough to match ordinary business conversation, so the skill may activate when the user did not intend analytical processing. In this skill's context that mainly risks unintended data access or generation of authoritative-looking analysis based on incidental mentions of performance, rather than direct code execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal