ClawHub
Back to skill

Security audit

Data Viz Reporter

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill for creating Chinese business data visualization reports, with no executable code or hidden access behavior.

Before using this skill, remove or mask personal, regulated, financial, or confidential fields unless you are comfortable sharing them with the agent session. The skill appears to be documentation-only and does not itself install code or access systems.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Confidence
91% confidence
Finding
The skill explicitly asks users to provide raw business data in formats like Excel, CSV, and JSON, but it does not include clear privacy guidance, data minimization instructions, or handling safeguards. This creates a real risk that users will submit sensitive commercial, financial, or personal data without understanding exposure, especially because the skill also encourages report generation from appended raw datasets.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
All user-facing instructions, templates, and examples are presented exclusively in Chinese, and the skill does not indicate that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Static analysis

No suspicious patterns detected.