ClawHub

debate-4person

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only debate simulator with disclosed web-search/API-key use and no evidence of hidden execution, persistence, data theft, or destructive behavior.

Safe to install for debate practice. Use it only for non-sensitive topics if web search is enabled, because debate queries may go to Tavily; verify important statistics or citations before relying on them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill defines fuzzy trigger phrases such as everyday conversational language that can match normal chat intent too broadly. This can cause unintended activation of the debate workflow, leading the agent to switch modes unexpectedly and produce structured multi-turn content the user did not explicitly request.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The read_when conditions are broad and ambiguous, for example matching any situation where the user 'wants a standard debate' or 'needs AI to simulate a debate scene.' Such loose activation constraints increase the chance the skill is loaded in contexts where the user only wants information or casual discussion, which can override safer or more appropriate behaviors.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal