Security audit
Do Things That Don't Scale
Security checks across malware telemetry and agentic risk
Overview
This is a simple startup-advice skill that gives strategic guidance and does not request sensitive access or run code.
This skill is appropriate to install if you want startup strategy prompts about doing manual, concierge-style work before automation. It includes external deciqAI/GitHub links in the footer, but it does not instruct the agent to open them or grant any sensitive permissions.
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.
Static analysis
No suspicious patterns detected.