ClawHub
Back to skill

Security audit

ThinkForce

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly coherent for managing ThinkForce missions, but it includes high-impact automation paths that can run agents from external webhook input without documented validation or approval controls.

Install only if you intend this skill to operate your ThinkForce workspace via API key. Be especially careful with scheduled or webhook-triggered subtasks: do not expose webhook URLs to untrusted senders, and avoid giving webhook-triggered agents access to sensitive connectors, credentials, or destructive tools unless you have separate validation and approval controls.

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
82% confidence
Finding
The skill instructs the agent to automatically fetch and cache organizational metadata such as company ID, name, status, and agent counts at session start without an explicit user-consent or disclosure boundary. In a multi-tenant or privacy-sensitive environment, this broadens data access beyond the user's immediate request and may expose internal organizational context unnecessarily.

Missing User Warnings

High
Confidence
93% confidence
Finding
The skill describes webhook-enabled subtasks that automatically run and append arbitrary POST payloads into the subtask prompt, but it does not require payload authentication, origin validation, replay protection, or prompt-injection safeguards. This creates a direct path for untrusted external input to trigger agent execution and influence downstream actions, including tool use and mission state changes.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.