ClawHub
Back to skill

Security audit

Relate Coach

Security checks for vulnerabilities and agentic risk

Overview

Relate Coach is a coherent communication-coaching skill with local scripts and no evidence of hidden data access, persistence, or unsafe authority.

This skill is appropriate for low-stakes relationship and communication coaching. Users should treat it as self-help scripting support, not professional counseling, legal advice, crisis help, or a tool to act on someone else's behalf.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · scripts/handler.py (reported line 134)May include surrounding context.

python
PLAYBOOKS = {
    "communication": {
        "title": "Clear Conversation Starter",
        "summary": "Use this when you know you need to talk, but keep rambling, softening the point, or waiting too long.",
        "best_for": [
            "bringing up a small but important issue",

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.