ClawHub
Back to skill

Security audit

Chat Rooom

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local coordination helper that stores chat-room notes and preferences on the user's machine, with no evidence of exfiltration, hidden execution, or destructive behavior.

Before installing, decide whether you want agents to create local .chat-rooom/ workspace logs and ~/chat-rooom/ preference files. Do not use the room files for secrets, tokens, or unrelated private data, because they are operational logs meant to be read by collaborating agents.

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
87% confidence
Finding

The setup instructs the skill to activate 'whenever the user asks multiple agents to collaborate' and possibly 'proactively when work splits into parallel tracks,' but it does not define precise trigger phrases, scope limits, or exclusion examples. This ambiguity could cause unintended activation during ordinary multi-step work or casual mentions of collaboration.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.