类案检索验证
Security checks across malware telemetry and agentic risk
Overview
This skill is a plain legal research prompt that helps users validate statutory analysis against real cases and does not request sensitive access or perform actions on its own.
Install this if you want Chinese legal-analysis prompts for checking statutes against real judicial practice. Because legal AI output can be unreliable, follow the skill’s own warning to verify any cited cases and holdings in authoritative legal databases before relying on them.
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.