ClawHub
Back to skill

Security audit

Linkedin Post Writer

Security checks across malware telemetry and agentic risk

Overview

This is a LinkedIn writing helper with no executable code, persistence, credential use, or hidden data flow.

Installers should treat this as a content-writing skill. It may read local brand, voice, and audience notes to tailor output, so avoid putting secrets or private client details in those source files unless you intend the agent to use them in drafting.

SkillSpector

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

Vague Triggers

Medium
Confidence
90% confidence
Finding
The manifest description includes very broad trigger phrases such as "LinkedIn" and general requests for professional/B2B social content, which can cause the skill to activate for loosely related or ordinary writing requests. Over-broad routing is dangerous because it can misclassify user intent, bypass more appropriate narrower skills, and produce behavior the user did not explicitly request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.