ClawHub
Back to skill

Security audit

groupchat-host

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed group-chat coordinator that forwards messages to selected agents with bounded runtime state and no persistence or hidden data access.

Install this if you want an agent to coordinate multi-agent conversations. Be aware that ordinary requests for a roundtable or informal join/leave statements may cause the skill to engage, so use explicit `!gc` commands when you want precise control over who receives the conversation.

SkillSpector

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The 'When to Use' section allows activation on broad natural-language requests such as 'User requests a roundtable or discussion between agents' and especially agent utterances like 'I'd like to join' or 'I'm leaving this chat.' These phrases overlap with ordinary conversation and do not define clear constraints or exclusions, which could cause unintended invocation of the skill.

Static analysis

No suspicious patterns detected.