ClawHub
Back to skill

Security audit

演示文稿生成工具

Security checks across malware telemetry and agentic risk

Overview

This presentation-generation skill is not malicious, but it requests broad read/write/command authority while describing a wider file-processing role than its stated purpose needs.

Review this skill before installing if you only want a presentation generator. Use it only with explicit input files or URLs you intend to process, avoid sensitive documents unless needed, and confirm any command execution or external API use before allowing the agent to proceed.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description says it should be used for broad 'file processing, document conversion, format conversion, and content extraction' tasks, which are generic triggers unrelated to a narrowly scoped presentation generator. In an agent environment with read/write/exec tools, this can cause over-invocation and lead the agent to apply a high-privilege skill in contexts where the user did not intend file access, command execution, or external processing.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill exposes read, write, and exec capabilities and references API usage, but the user-facing description does not prominently warn that invoking it may read local files, write output artifacts, call external services, or execute system commands. This reduces informed consent and increases the chance that sensitive data is processed or commands are run unexpectedly under an overly generic workflow description.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.