ClawHub

ThinkForce

Security checks across malware telemetry and agentic risk

Overview

The skill is a documentation-only ThinkForce API helper whose account access and mission actions are disclosed and aligned with its purpose.

Install only if you intend to let the agent operate your ThinkForce workspace with your API key. Review actions that run agents, attach connectors or credential tools, enable schedules/webhooks, create public share links, invite collaborators, or delete/cancel work; these are legitimate features but can affect account data, costs, and external visibility.

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
75% confidence
Finding
The skill directs the agent to use a user API key to query company identity and operate on account-scoped resources, but it does not prominently require explicit user consent or warn that sensitive tenant context will be transmitted to a third-party service. This can lead to privacy surprises and inadvertent use of privileged account context beyond what the user expected.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents share and invite flows that expose mission content externally, but the warning is not prominent where the feature is introduced. Although later text says not to share or invite without consent, these endpoints can disclose mission data or collaboration access if triggered without the user fully understanding the exposure.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal