AI提示词工程专家
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-engineering teaching skill made only of Markdown guidance, with no executable code, hidden access, persistence, or credential handling found.
Before installing, users should expect this skill to influence how the agent helps write prompts, including structured formats and reasoning-pattern templates. It does not appear to add executable behavior or access private data.
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.