协作造技师
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only workflow skill for turning collaborative human-agent processes into reusable skills, with the main caution being its disclosed suggestion to save design rationale in memory.
Safe to install as a workflow aid. Before letting it save anything to memory, review the proposed summary and remove confidential project details, private chat excerpts, credentials, or unstable ideas that should not influence future sessions.
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
59/59 vendors flagged this skill as clean.