ClawHub
Back to skill

Security audit

数据处理脚本生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Excel/ERP report-script helper with no bundled executable code, persistence, or hidden data movement.

Installers should treat this as a spreadsheet automation helper. Users should share only the Excel/CSV samples needed for the report, review generated Python scripts before running them, and confirm any local paths used in the script.

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
  • 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)

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The manifest description and invocation examples are written as directives entirely in Chinese, with no indication that other languages are supported or that the user may choose their preferred language. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are broad enough to match many generic automation or scripting requests, which can cause the skill to activate outside its intended scope. In this skill, that matters because it instructs collection of local file paths, uploaded Excel/CSV samples, and generation of runnable scripts, increasing the chance of unintended handling of sensitive business data or inappropriate delegation to a specialized workflow.

Static analysis

No suspicious patterns detected.