ClawHub
Back to skill

Security audit

Roadshow Planning

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language roadshow and fundraising presentation planning skill with no code execution, persistence, or hidden data handling.

Before installing, users should understand that the skill is intended for Chinese-language fundraising roadshow preparation and may ask for sensitive company, team, and financial details. Only provide business plan files or financial data you are comfortable using for that purpose.

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
93% confidence
Finding

The description says to use the skill whenever the user needs to plan a roadshow, prepare a financing presentation, write an executive summary, describe a business model, or introduce the team. Several of these triggers are broad business-assistance requests rather than narrowly scoped invocation conditions, which increases the risk of unintended activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file is entirely written as a Chinese-language skill and does not state that output language should follow the user's preference or that the Chinese locale is required for a justified regional use case. This can violate language/locale policy by implicitly constraining interactions to a single language without opt-in.

Content

No source excerpt is available for this finding.