ClawHub
Back to skill

Security audit

groupchat-host

Security checks for vulnerabilities and agentic risk

Overview

This skill is a bounded group-chat coordinator that discloses its cross-agent messaging behavior and does not include code, persistence, credential access, or hidden install behavior.

Install this only if you want the host agent to relay your group-chat messages to named participant agents. Be aware that participant agents may be able to join or leave through the documented group-chat workflow, so use explicit participant commands and end the chat when you no longer want messages forwarded.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation guidance includes broad triggers such as generic user requests for talking to multiple agents and participant self-initiated join/leave statements. This can cause the skill to activate in contexts where the user did not explicitly intend to start or modify a group chat, increasing the risk of unintended cross-agent messaging, privacy leakage, and avoidable message amplification.

Content

No source excerpt is available for this finding.