ClawHub

life-coach

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Chinese life-coaching prompt skill with visible boundaries and no evidence of hidden code, data access, or persistence.

Use this only if you want Chinese-language reflective coaching for ordinary goal clarification, decisions, and emotional support. Do not rely on it for self-harm, violence risk, medical or psychological diagnosis, therapy, legal advice, or financial advice; in urgent or high-risk situations, contact local emergency services or a qualified professional.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill is scoped to a very broad set of common emotional and life-problem scenarios without clear invocation constraints, which increases the chance it will be used in borderline mental-health situations beyond its safe operating boundary. In a coaching persona that offers emotional support, broad applicability can lead to over-reliance, misrouting of high-risk users, or inappropriate handling of serious distress before escalation safeguards are triggered.

Natural-Language Policy Violations

Medium
Confidence
73% confidence
Finding
Mandating Chinese-native-style communication without offering a user language choice can create consent and comprehension issues, especially if the surrounding system or user expects another language. In a support-oriented skill, forced language/style can reduce clarity around boundaries, safety disclaimers, and escalation guidance, which is more concerning when users are distressed or vulnerable.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal