Security audit
AI提示词工程专家
Security checks across malware telemetry and agentic risk
Overview
This is a Markdown-only prompt-engineering guide that teaches prompt structure and does not add executable behavior or request private access.
Before installing, expect this skill to guide the agent toward structured prompt-writing advice and Chinese-language output. It does not appear to execute code, access private data, install dependencies, or persist anything in the environment.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.