ClawHub
Back to skill

Security audit

ppt-turn-web-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a tutorial-page helper that reads user-provided tutorial materials and creates local HTML/style files, with no evidence of hidden execution, exfiltration, or privileged persistence.

Install only if you want an agent to turn procedural material, screenshots, videos, and links into local tutorial HTML pages. Review generated files before publishing them, and be aware that the included configuration question may appear in Chinese even in other-language conversations.

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
95% confidence
Finding

The skill description is broad enough to match many generic requests about guides, walkthroughs, branding, setup, or procedural content, which can cause the agent to invoke this skill in situations the user did not specifically intend. That increases the chance of context hijacking, inappropriate file reads/writes, or unexpected transformation of user content, especially because the skill instructs the agent to read and create files as part of normal operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill hard-codes a Chinese-language configuration prompt without checking the user's language, which can degrade transparency and informed consent during an important configuration step. This is primarily a safety and usability issue: users may misunderstand options, approve defaults unintentionally, or be unable to verify what changes are being requested.

Content

No source excerpt is available for this finding.