ClawHub
Back to skill

Security audit

execution-coach

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only coaching skill with no code or data access, but it uses a blunt style and broad triggers that users should opt into deliberately.

Install this only if you want a direct Chinese-language execution coach that may interrupt hesitation, limit options, and ask for concrete follow-through. Consider narrowing activation or disabling proactive audits if you do not want forceful coaching during ordinary planning, shopping, learning, or reflection.

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
91% confidence
Finding
The activation conditions are broad behavioral cues that can match many normal user interactions, such as comparing options, discussing meaning, or hesitating before a purchase. Because the skill is designed to intervene forcefully and steer the conversation, unintended activation can override user intent, reduce autonomy, and cause inappropriate advice in benign contexts.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill content is written entirely in Chinese and does not indicate any language negotiation, fallback behavior, or locale requirement. If invoked for users who are not comfortable with Chinese, the model may respond in an inaccessible language, leading to misunderstanding of instructions and degraded safety, especially because the skill uses terse and directive coaching language.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.