Back to skill

Security audit

JW Data Analyst

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese-language data analysis skill with no bundled executable code, persistence, credential handling, or hidden behavior.

Install this if you want a Chinese-language data analysis helper. Review data before sharing it with the agent, especially database/API sources or sensitive spreadsheets, and choose output paths deliberately because the skill says charts default to a D: drive location.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description includes broad trigger phrases such as '数据分析、图表、统计、报表、可视化' that are common in ordinary user conversations. This can cause the skill to activate outside narrowly intended contexts, increasing the chance it handles unintended files, data sources, or requests and expands its effective attack surface.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest and usage instructions consistently assume Chinese-language interaction, but the file does not state that the skill is region-specific or provide an opt-in language/locale choice. This can violate language or locale policy when users are implicitly forced into a single language without consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.