ClawHub
Back to skill

Security audit

AI Detector & Humanizer for LinkedIn/X Posts

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward social-post analyzer that sends drafts to a disclosed SocialNexis API and does not install code or request credentials.

Before using this skill, understand that the post draft you submit will be sent to SocialNexis for analysis. Avoid sending confidential, regulated, or proprietary drafts unless you are comfortable with that third-party data flow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill description contains broad trigger phrases such as requests to 'check, score, humanize, or de-AI a social post draft' and 'does this sound AI-written?', which can cause the skill to activate for a wide range of ordinary writing-assistance queries. Over-broad activation increases the chance that users' draft content is routed to this skill unexpectedly, which is especially risky because the skill sends post text to an external service.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to POST the user's draft to external SocialNexis API endpoints but does not warn that the content leaves the local environment. Because social posts may contain unpublished marketing copy, personal data, or sensitive business information, this omission can lead to inadvertent third-party disclosure without informed user consent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.