ClawHub
Back to skill

Security audit

企业客户画像分析

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a public-information business customer profile report generator, with broad activation wording but no hidden access or unsafe behavior found.

Before installing, review the trigger phrases and use this skill for intended enterprise customer-profile or due-diligence analysis. Avoid providing private customer lists or confidential business data unless you want the agent to use that information in the report, and confirm ambiguous business-analysis prompts should use this customer-profile workflow.

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 (2)

Vague Triggers

Medium
Confidence
85% confidence
Finding
These trigger conditions are broad enough to match many ordinary enterprise-analysis requests, increasing the chance the skill is invoked outside a user's explicit intent. Over-broad invocation can route sensitive business-analysis prompts into a workflow that performs extensive web searches and profiling logic the user did not specifically request.

Vague Triggers

Medium
Confidence
89% confidence
Finding
Several listed trigger phrases are generic business-analysis requests that overlap with other legitimate skills or general assistant behavior. In practice, this can cause unintended skill activation, leading to unnecessary collection, synthesis, and presentation of potentially sensitive corporate relationship data under an overly expansive workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.