ClawHub
Back to skill

Security audit

Html Presentation Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent as a presentation generator, but it automatically includes web research and final deployment without clearly scoping user consent, destination, or visibility.

Review before installing if you do not want a generic presentation or report request to trigger web access, image generation, file creation, and deployment. Use it only when you are comfortable confirming where the final presentation will be published and whether the topic content may be sent to external services.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad, common terms like "presentation," "report," and multilingual equivalents that can cause the skill to activate in many ordinary conversations unrelated to an explicit request for this tool. Over-broad invocation increases the chance the agent will enter a workflow that performs file generation, image generation, research, or deployment unexpectedly, which can amplify downstream risky behaviors.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow explicitly instructs the agent to search the web and deploy a final presentation, but it provides no requirement to inform the user or obtain consent before performing network activity or publishing output. In context, this is more dangerous because the skill is designed to autonomously execute a full pipeline, so unexpected external access and deployment could expose sensitive prompts, proprietary content, or create unintended public artifacts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instructions require all output to use Times New Roman for both Chinese and English text, imposing a fixed presentation locale/style choice regardless of user preference. This is a natural-language policy issue because it forces a specific formatting convention without offering user choice or explaining a justified regional/compliance need.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.