ClawHub

Skillboss

Security checks across malware telemetry and agentic risk

Overview

This is a small user-run connector for the SkillBoss/HeyBoss AI gateway, with expected remote API use and no hidden persistence or local data harvesting found.

Install only if you intend to use SkillBoss/HeyBoss as an external AI service. Treat SKILLBOSS_API_KEY as a secret, avoid submitting confidential or regulated data unless you trust the provider's terms, and monitor usage or billing for the API key.

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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly encourages sending prompts to a third-party multi-provider AI gateway but does not disclose that user input and generated outputs may leave the local environment and be processed by external services. This can lead to unintended disclosure of sensitive data, especially because users may assume a local or single-provider workflow and may not realize prompts could be routed across multiple downstream providers.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The documentation tells users to obtain and use an API key but provides no guidance that the key is sensitive or how it should be stored and handled. This increases the chance of accidental exposure through shell history, logs, screenshots, shared environments, or hardcoded configuration.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script sends user-supplied prompts and the API key to a third-party service without any explicit disclosure, confirmation, or redaction safeguards. In a CLI skill that may be used inside larger agent workflows, this can cause users to unknowingly transmit sensitive prompts, secrets, or proprietary data off-host to an external provider.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal