ClawHub
Back to skill

Security audit

ppt-visual-designer

Security checks for vulnerabilities and agentic risk

Overview

This is a presentation-design instruction skill with no hidden code, persistence, credential use, or external access.

Installers should expect this skill to influence presentation and slide-design requests, especially Block-style PPT work. Be aware that the trigger may be broader than ideal and the instructions are written in Chinese, so ambiguous 'block' or slide-related requests could route here.

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
Confidence
95% confidence
Finding
The trigger criteria are broad enough to match many ordinary requests about PPTs, slides, or any mention of 'block', which can cause unintended skill invocation. This creates routing and prompt-scope risk: the agent may activate this skill when the user did not want a visual-design transformation, leading to incorrect behavior, context hijacking, or interference with more appropriate skills.

Natural-Language Policy Violations

Medium
Confidence
83% confidence
Finding
The natural-language content of the skill is written entirely in Chinese and instructs the agent role and workflow in that language, but does not state that the user may choose another language. This can constitute a language/locale policy issue because the skill appears to impose a specific language without explicit user opt-in or a documented region-specific justification.

Static analysis

No suspicious patterns detected.