ClawHub
Back to skill

Security audit

测试用例表编写

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for creating and updating Excel test-case tables, with one ordinary file-overwrite caution users should handle deliberately.

Before installing or using it, treat workbook writes as real file changes: ask the agent to confirm the exact Excel file path, avoid overwriting existing workbooks unless intended, and request a backup or timestamped output file when editing important test assets.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill includes concrete code that creates and saves an Excel file using a fixed filename and later reopens and saves that same file again, which can overwrite existing user data without any confirmation, backup, or warning. In an agent setting, file-modifying actions based on implicit assumptions are risky because they can cause silent data loss or unintended modification of an existing workbook.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructions and usage guidance are entirely in Chinese, which can impose a language constraint on users without any opt-in or explanation. Under the stated policy, forcing a specific language without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.