ClawHub
Back to skill

Security audit

导购结构分析

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to perform the advertised retail clerk analysis, but it loads unreviewed local code and fetches sensitive staff performance data through an undeclared API client.

Review before installing or running. Only use this skill with permission to access the store and employee performance data, and ask the publisher to package or declare the API client, remove the developer-local import path, and document what credentials and store access controls are used. No malicious behavior or persistence was found in the provided artifacts, and VirusTotal was still pending.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The code prepends an absolute developer-local path to sys.path and then imports api_client from outside the skill directory. This expands the skill's trust boundary to arbitrary workspace code on the host, enabling unintended code execution or access to local modules that are unrelated to the stated clerk-analysis purpose.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger conditions are broad, natural-language business queries such as asking how the clerk team is structured or who caused performance decline. This can cause the skill to activate in ordinary conversation without strong user intent, leading to over-collection, misrouting, or unsolicited personnel-performance analysis on potentially sensitive employee data.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill fetches store and clerk performance data from an API endpoint without any user-facing notice, consent flow, or data minimization controls. Because this is employee performance data, silent retrieval can expose sensitive business and personnel information to users who may not expect or be authorized for that access.

Static analysis

No suspicious patterns detected.