ClawHub
Back to skill

Security audit

Content Ideas Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward content outlining helper that fetches only user-provided URLs and saves the generated outlines to a disclosed local markdown file.

Install is reasonable for a content workflow. Only provide URLs and source material you want the agent to retrieve, analyze, and store locally; avoid private/internal links or confidential material unless that is intentional. Review the generated outlines before publishing because the style instructions favor strong, absolute language.

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
92% confidence
Finding
The skill explicitly accepts user-provided URLs via web_fetch and saves generated output to a local file, but the description does not warn users about either behavior. This can undermine informed consent and create privacy or data-handling risks, especially if users provide sensitive source material or do not expect persistent storage.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.