Chudaxia Ai Coach Tools Position Agent Prompts Generator

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only workflow for turning job descriptions into structured AI agent prompts, with disclosed knowledge-base lookup and no hidden execution or persistence.

Install this if you want an agent to generate role-based system prompts from job descriptions. Before use, confirm which knowledge base it may search and review generated prompts before deployment, especially permissions, compliance boundaries, and any inferred job responsibilities.

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
93% confidence
Finding
The skill’s activation description is overly broad, matching generic requests about job descriptions,岗位职责, AI Agent prompts, and related topics without strong disambiguation. This can cause unintended invocation of the skill in unrelated contexts, increasing the chance that the agent retrieves and transforms sensitive HR or internal documentation when the user did not explicitly request this specialized workflow.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal