Linkedin Comment Drafter

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.0.0

Overview

This is an approval-gated LinkedIn comment drafting skill with optional posting support, and the reviewed artifacts do not show hidden or destructive behavior.

Install only if you are comfortable reviewing LinkedIn comments before they are posted. Keep manual mode if you do not want automated posting, and only configure Publora or LINKEDIN_SKILLS_CUSTOM_POSTER with credentials or commands you trust, because approved drafts and target URLs may be passed to those systems.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: This markdown file documents a `diy` mode that invokes a user-configured custom poster command with the drafted comment text and target URL as arguments. That behavior can transmit user content to an external command and affect system integrity, but the skill description does not include an explicit warning about this risk.

VirusTotal

66/66 vendors flagged this skill as clean.