ClawHub
Back to skill

Security audit

Linkedin Post Writer

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only LinkedIn writing helper that may draft and schedule posts only after user approval, with no executable code or hidden installation behavior.

Install only if you want LinkedIn post drafting assistance. Review generated posts before approving publication or scheduling, and be aware the invocation wording may make the skill appear for some general post-writing requests.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to trigger on generic writing requests such as 'write me a post' or 'needs a hook,' which overlaps with common assistant behavior and can cause the skill to activate when the user did not explicitly request this specialized workflow. That increases the chance of unintended tool use, formulaic content generation, or scheduling-related actions being introduced into otherwise ordinary writing interactions.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The 'When to use' bullets contain ambiguous triggers like 'topic + rough angle,' 'known-winning formats,' and 'audit + schedule in one flow,' without tight exclusion boundaries. In an agent environment, these vague conditions can cause over-selection of the skill for broad content-help requests, potentially steering users into publishing-oriented flows or adjacent actions they did not intend.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.