qy-123
Security checks across malware telemetry and agentic risk
Overview
This is a text-only coding-guidance skill with no executable code, credentials, persistence, or network behavior detected.
This skill appears safe to install if you want stricter coding-process rules applied during development work. Be aware it is intentionally broad and may make an assistant more rigid about tests, error handling, and debug-log workflow, but there is no evidence of hidden execution or data access.
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.
