ClawHub
Back to skill

Security audit

Blog Writer

Security checks across malware telemetry and agentic risk

Overview

This blog-writing skill is coherent and disclosed, but users should know it is designed to publish drafts to a specific Notion database and keep finalized posts as future examples.

Install this only if you want a personal blog-writing workflow that can send draft content to the configured Notion database. Avoid using it with sensitive research or private notes unless you are comfortable with that Notion publication step, and review finalized examples before letting them persist for future style matching.

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
83% confidence
Finding
The trigger conditions are broad enough that the skill may activate on vague requests like writing 'in my style' or using provided links, causing it to ingest user materials and potentially auto-publish content when the user did not intend to invoke this workflow. In this skill, overbroad activation is more dangerous because later phases mandate external transmission to Notion and persistence of content.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill mandates publishing full draft content to a specific Notion database 'even if not yet finalized' and defines failure as not transmitting the content externally. This creates a clear data-exfiltration and privacy risk: sensitive drafts, proprietary research, or personal notes may be sent to a third-party service without explicit, contextual user consent each time.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.