ClawHub
Back to skill

Security audit

OpenClaw Marketing OS

Security checks across malware telemetry and agentic risk

Overview

This markdown-only skill is not malicious, but it directs agents to publish content, send lifecycle emails, and update records without clear approval or scope limits.

Install only if you intend an agent to help operate real marketing workflows. Before connecting tools or logged-in sessions, define the allowed platforms, accounts, campaigns, audiences, file locations, and daily volume limits, and require human approval before any public post, blog publish, customer email send, or account-data writeback.

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
88% confidence
Finding
This markdown file describes operational behaviors including lifecycle email sends, publishing, and writeback/accounting, which can affect user data, privacy, and external systems. Under SQP-2 for markdown files, the description should include a clear warning or disclosure about these potentially impactful actions, but none is present in this section or the surrounding skill description.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal