ClawHub
Back to skill

Security audit

Pans Discovery Playbook

Security checks across malware telemetry and agentic risk

Overview

This skill is a local AI compute sales playbook generator, with only a minor risk of activating too broadly.

Install if you want a local sales discovery guide generator. Invoke it by name or with a specific scenario and industry to avoid accidental activation, and be careful if you fill the generated templates with confidential customer contact, budget, or procurement details.

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
92% confidence
Finding
The trigger phrases are very broad and include generic sales and communication terms such as 'discovery', '首次沟通', and '客户沟通', which can cause the skill to activate in many unrelated contexts. Over-broad invocation increases the chance of unintended routing, prompt/context leakage into the skill, and misuse in conversations that did not intend to invoke this specialized playbook.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.