TOSR Test Skill

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only test skill that openly describes live ClawHub lifecycle API actions, including deletion, but does not bundle code or hidden behavior.

Install or invoke this only if you intentionally want to run a ClawHub lifecycle test. Use a test account or disposable test skill, confirm the exact slug before publish/update/delete steps, and avoid running it with production credentials unless that is deliberate.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill explicitly describes performing create, update, and delete operations against the real API, but it does not present a clear warning, confirmation gate, or safety constraints around those live and destructive effects. Even if intended for testing, documentation that normalizes real-environment mutation without explicit safeguards can lead operators or agents to run destructive actions unintentionally.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal