ClawHub
Back to skill

Security audit

报表官-图表生成

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language chart-code generator with no bundled executable files, persistence, or hidden authority.

Use this skill when you intentionally want chart code for supported spreadsheet/document tools. Review generated VBA, macros, or scripts before running them in a target application, and only submit dataset IDs or visualization specs that are appropriate for the backing API to process.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The natural-language triggers are very broad generic phrases such as '帮我画个柱状图' and '生成图表代码', which can overlap with ordinary user requests and cause the skill to activate unexpectedly. Because this skill emits executable code for external tools (including VBA, scripts, and macros), accidental invocation can increase the chance of unsafe code generation or insertion into documents without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

Natural-language content throughout the file forces a single language for descriptions, parameters, triggers, and constraints, with no opt-in or alternative locale. Under the stated policy, language-specific behavior should either offer user choice or clearly justify the locale limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.