ClawHub

B2c Marketing 1.0.1

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent marketing playbook that can post or schedule content to real social accounts, with no hidden code or deceptive behavior found.

Install only if you want an agent helping with real social-media marketing. Keep the Post Bridge API key private, avoid committing the .env file, connect only intended accounts, verify the publisher/version, and require explicit approval of caption, media, platforms, accounts, and schedule before any post is created.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the user to place a live Post Bridge API key directly in a workspace .env file but does not warn that the credential is sensitive, should be access-restricted, or must not be logged, committed, or exposed to other tools in the workspace. In an agent environment, workspace files may be broadly readable by other skills, processes, or accidental outputs, increasing the risk of credential leakage and unauthorized posting on linked social accounts.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill directs automated posting and scheduling to TikTok, Instagram, and YouTube through an external API without an explicit warning that content will be published to real third-party accounts. That creates a risk of unintended or unauthorized public posting, especially in agentic workflows where users may assume actions are draft-only or internal unless clearly told otherwise.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal