ClawHub

Caring CourseForge

Security checks across malware telemetry and agentic risk

Overview

This CourseForge skill is mostly transparent and purpose-aligned, but it exposes broad account-changing powers that users should review before installing.

Install only if you trust CourseForge and the npm MCP client with your CourseForge account. Use the least-privileged API key available, avoid API-key administration unless you truly need it, and require explicit user confirmation before deletes, revocations, rollbacks, storage cleanup, uploads, scraping, exports, or auto-fix actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

High
Confidence
95% confidence
Finding
API key creation and revocation are administrative security-sensitive actions that exceed the stated purpose of creating and managing course content. Exposing these capabilities inside a broad course-authoring skill increases the chance that prompt injection, user confusion, or agent overreach could rotate credentials, create persistent access, or disrupt integrations.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill exposes numerous destructive operations such as deleting courses, lessons, documents, storage files, revoking API keys, and automatic modification actions, but it does not warn that these actions may be irreversible or require explicit confirmation. In an agent setting, this increases the chance of accidental or over-broad execution that can cause data loss or operational disruption, especially because the skill is framed as a general-purpose management interface with many high-impact tools.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises AI, web search, URL fetching, scraping, document upload, and content analysis capabilities without warning that course materials, prompts, uploaded documents, or fetched data may be transmitted to external services. This can lead to unintended disclosure of proprietary, regulated, or personal data because users and agents are not prompted to assess sensitivity before sending content off-platform.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal