ClawHub
Back to skill

Security audit

创建检查编辑

Security checks across malware telemetry and agentic risk

Overview

This is a simple PowerPoint/PPTX helper skill with broad but purpose-aligned file and command permissions, and no hidden installer, persistence, or data exfiltration behavior found.

Install only if you want an agent to help create or edit PowerPoint files. Give it specific file paths and review any proposed shell commands or file writes before allowing changes, especially when working with sensitive presentations.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is overly broad and underspecified while the metadata grants powerful tools including read, write, and exec. In an agent setting, ambiguous invocation criteria can cause the model to apply the skill in inappropriate contexts, potentially leading to unintended command execution or file modification beyond user expectations.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill exposes file modification and command execution capabilities but does not prominently warn users that invoking it may alter local files or run shell commands. In an agent context this is dangerous because users may supply untrusted content or broad instructions, and the agent could execute commands or overwrite files without informed consent or sufficient scrutiny.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.