ClawHub
Back to skill

Security audit

Strategic Reading

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward reading-analysis template, with only a disclosed local note-saving step to be aware of.

Before installing, understand that the skill may create or update a local reading/project note when used. Provide only source text you are comfortable analyzing, and confirm the destination path if you do not want automatic note saving.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill explicitly instructs the agent to 'Write to knowledge base' and save output under a project or reading directory, but it does not warn the user that running the skill may modify local files. That creates a real, though low-severity, safety issue because users may invoke what appears to be an analysis-only skill without realizing it has persistence side effects.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.