ClawHub
Back to skill

Security audit

Clawpost

Security checks across malware telemetry and agentic risk

Overview

This is a coherent ClawPost social publishing skill, but it lets an agent publish or schedule public LinkedIn/X posts through a connected account without built-in confirmation guidance.

Install only if you trust ClawPost with the connected LinkedIn/X accounts and are comfortable giving the agent posting authority. Keep CLAW_API_KEY secret, connect only intended accounts, and require the agent to confirm the exact platform, content, and timing before any publish, schedule, update, or delete action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill provides immediate publish and scheduling commands that send user-authored content to a third-party service and can cause posts to appear on linked LinkedIn/X accounts, but it does not explicitly warn the user before those actions. In an agent context, this increases the risk of unintended external actions, accidental disclosure of sensitive content, or posting without sufficiently informed consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.