ClawHub

ppt-skill2

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent presentation-generation helper with normal file-writing and browser-preview behavior for that purpose.

Install/use this for Reveal.js presentation creation if you are comfortable with generated decks fetching CDN JavaScript when opened. Choose output paths carefully to avoid overwriting files, and run the Puppeteer/decktape checking steps only on decks you created or trust.

SkillSpector

By NVIDIA
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
Confidence
90% confidence
Finding
The trigger list contains broad generic terms such as '演示', '展示', and 'presentation' that can appear in many normal conversations unrelated to slide generation. This can cause unintended skill activation, leading the agent to override user intent, inject large HTML/JS outputs unexpectedly, or route benign queries into a more privileged content-generation path.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill metadata and instructions are written entirely in Chinese and do not provide any mechanism to honor the user's preferred language. In a multilingual agent, this can cause the skill to activate and respond in an unexpected language, degrading transparency and increasing the chance that users cannot adequately review generated HTML, scripts, or external-resource behavior.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list is broad and includes common terms such as 'presentation', 'slides', 'deck', '展示', and '汇报', which can appear in many ordinary requests. This can cause the skill to activate unintentionally, increasing the chance of prompt hijacking, incorrect routing, or unwanted handling of user requests outside the intended scope.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal