Security audit
Skill结构拆解引擎
Security checks across malware telemetry and agentic risk
Overview
This is a narrow Markdown-only skill that helps decompose complex tasks into independent sub-skills and does not request code execution, credentials, persistence, or broad system access.
Install this if you want a Chinese-language orchestration helper for decomposing complex tasks into skill definitions. Review the generated sub-skill plan before downstream agents act on it, because this skill designs structures but does not itself enforce safe execution.
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.