三省六部技能映射
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only planning template for organizing multi-agent work, with no executable code or hidden access behavior found.
Install this if you want a reusable planning template for 三省六部-style multi-agent coordination. Review any separately invoked skills that actually perform GitHub actions, spawn sub-agents, build MCP tools, or analyze project data, and keep user approval around actions that modify repositories or project state.
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
66/66 vendors flagged this skill as clean.