ClawHub
Back to skill

Security audit

Data Analyst Cn Free

Security checks for vulnerabilities and agentic risk

Overview

This is a simple data-analysis guidance skill whose read, execute, and write capabilities are generally aligned with CSV/Excel analysis, though users should be aware it may run code or create outputs.

Install only if you want a Chinese-language helper for basic CSV/Excel analysis. Review any generated Python before running it, keep original data files backed up, and direct outputs to a known location because the skill has execution and write capability.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill summary/description is broad and generic, advertising reusable workflows for loosely defined 'related development scenarios' without clearly constraining when the skill should be invoked. In an agent environment, vague trigger boundaries can cause over-invocation on unrelated tasks, increasing the chance the skill reads, executes, or writes in contexts the user did not specifically intend.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill declares powerful tools including exec and write, and the documentation presents data cleaning and processing flows that can modify outputs or files, but it does not prominently warn users that files may be changed or generated. This can lead to unintended data overwrites, unsafe code execution paths, or user confusion about side effects in an environment where the agent has filesystem access.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documentation states that SimHei Chinese font configuration '必须先执行', which imposes a specific locale/font setup rather than offering it as an optional choice. This is a natural-language locale policy issue because the skill forces one language-specific presentation path without user opt-in or alternatives.

Content

No source excerpt is available for this finding.