ClawHub
Back to skill

Security audit

Social Content Planner

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple local social-media content planner with no evidence of hidden access, persistence, credential use, or destructive behavior.

This appears safe to install as a lightweight local content-idea generator. Treat the advertised search-engine trend tracking as a feature that could expose research terms if added or performed by an agent later, and avoid using confidential client or campaign topics with online trend searches unless you approve that network use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
87% confidence
Finding
The skill states that it performs trend tracking by calling a search engine, but it does not warn users that external network requests may occur or that prompts, keywords, or other data may be transmitted to third parties. In a content-planning context this is not inherently malicious, but it can expose sensitive campaign topics, client information, or research terms without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.