AI心理疗愈师

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed mental-wellness coaching skill with no executable code, credentials, persistence, or hidden data flows, though users should treat its advice as support rather than professional care.

Install only if you want an AI mental-wellness support skill. Do not rely on it for diagnosis, treatment, emergencies, or crisis care; seek a licensed professional or emergency/crisis resources for serious distress or self-harm risk. Consider invoking it deliberately rather than letting ordinary emotional conversation automatically become a coaching session.

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
89% confidence
Finding
The invocation guidance is broad enough to match ordinary emotional conversation, such as casually describing stress, relationship conflict, or sleep problems. That can cause the skill to activate unexpectedly in general chats and steer users into quasi-therapeutic flows involving mental-health screening or advice without a deliberate opt-in, which is especially sensitive given the health context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal