ClawHub

Social Media Content Generator

Security checks across malware telemetry and agentic risk

Overview

The skill appears to generate local branded social media image assets, with documentation clarity issues but no evidence of hidden access, exfiltration, persistence, or destructive behavior.

Before installing, confirm you want a skill that creates branded social media image files locally. The publisher should update the description, docstring, and trigger wording for clarity, but the available evidence does not show behavior that requires Review.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The manifest says the skill generates social media posts for two brands, which implies text/content creation. The code instead defines image dimensions/templates and renders PNG graphics with PIL, saving branded image files to disk rather than producing post copy or publishing-ready social media text.

Intent-Code Divergence

Low
Confidence
85% confidence
Finding
The module docstring says "Social Media Content Generator for OpenClaw," while the manifest context says the skill is for LevelUpLove and PayLessTax brands. This documentation does not match the stated skill intent and can mislead reviewers about the actual target brands/purpose.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The listed triggers are generic operational modes rather than specific invocation conditions or phrases. Terms like 'API trigger' and 'Manual CLI execution' do not define scope, constraints, or exclusion cases, so the activation boundary is ambiguous.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal