ClawHub
Back to skill

Security audit

Emotional Wellness AI Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only emotional support skill with clear safety boundaries and no code, credentials, persistence, or hidden system access.

Before installing, consider that this skill may be invoked for broadly worded emotional topics and may provide supportive, mental-health-adjacent guidance. It should not be treated as therapy, diagnosis, medication advice, or crisis intervention, but the artifact itself does not show security-dangerous behavior.

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
93% confidence
Finding

The skill uses very broad trigger phrases such as 'feeling down', 'mood support', and 'psychological advice', which overlap heavily with ordinary conversation and can cause the skill to be invoked when the user did not explicitly request this specialized behavior. In an emotional-wellness context, unintended invocation is more concerning because the skill may steer general chats into quasi-therapeutic guidance, creating safety, consent, and routing risks for sensitive mental-health-adjacent interactions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.