ClawHub
Back to skill

Security audit

Mind Companion

Security checks for vulnerabilities and agentic risk

Overview

This is a simple emotional-support skill with no code or network behavior, but it needs review because it invites vulnerable personal disclosures without clear crisis boundaries.

Review before installing. This skill has no apparent technical execution or exfiltration behavior, but users may treat it as emotional support during serious distress. It should add clear crisis guidance, emergency escalation language, and tighter activation boundaries before being used as a trusted companion.

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 (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill frames itself as a 'safe, warm, judgment-free listener' for users who have troubles they cannot share with anyone else, but it does not provide prominent warnings that it is not a therapist, crisis resource, or substitute for professional help in high-risk situations. This can foster overreliance, especially among distressed users, and may delay appropriate escalation when users disclose self-harm, abuse, suicidality, or other acute mental-health crises.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad, conversational, and highly likely to match ordinary user speech, which can cause the skill to activate in situations beyond the user’s intent. In an emotional-support context, accidental routing is more sensitive because users may disclose vulnerable mental-health content to a skill that presents itself as a trusted companion without clear boundaries or escalation guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.