ClawHub
Back to skill

Security audit

Blog Content Planner

Security checks across malware telemetry and agentic risk

Overview

This is a simple blog-planning prompt skill, but its documentation includes unrelated payment upsell text users should treat as advertising.

Safe to install as a planning prompt skill. Ignore the payment and crypto text unless you independently intend to buy a separate Pro offering; the core skill should not require paying through links embedded in the skill file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (1)

Description-Behavior Mismatch

Low
Confidence
96% confidence
Finding
The skill metadata presents a benign blog-planning capability, but the body includes embedded payment solicitation, cryptocurrency wallet details, and upsell content unrelated to core execution. This creates a trust-boundary violation: users and agents may invoke the skill expecting planning help while being exposed to commercial or external-payment instructions that could be abused for spam, monetization, or social engineering.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.