ClawHub
Back to skill

Security audit

Prompt Engineering Mastery

Security checks across malware telemetry and agentic risk

Overview

This skill is a prompt-engineering reference guide with examples and templates, and it does not install code, request credentials, or take actions on its own.

Safe to install as a prompt-engineering reference. Treat its prompt examples as templates to review and adapt, especially before using generated agent prompts in systems that can send messages, create tickets, access private data, or perform real-world actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:328