ClawHub
Back to skill

Security audit

positive-psychology

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only emotional support skill with no technical access, but it needs review because it treats crisis language like ordinary coaching triggers without a clear safety path.

Review before installing if this agent may interact with users in emotional distress. It should not be relied on for emergencies, self-harm thoughts, or serious mental health situations unless a separate crisis-safety protocol is added that directs users to immediate human, local emergency, or qualified professional support.

SkillSpector

By NVIDIA
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
Confidence
94% confidence
Finding
The trigger list is broad enough to activate on common emotional language such as stress, loneliness, confusion, or despair, which can cause the skill to engage outside a narrowly intended context. In a mental-health-adjacent skill, over-triggering is risky because it may steer sensitive conversations into a fixed counseling style, including for users expressing crisis signals like '活不下去', without appropriate triage or safety escalation.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.