Security audit
Ai Metallurgy
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a markdown-only deliberate-practice coaching guide with no evidence of hidden execution, sensitive data access, or unsafe persistence.
This looks safe to install for practice-coaching use. As with any skill, review the markdown instructions if you rely on it for important learning or coaching workflows, but the available evidence does not show hidden execution, credential handling, or privileged behavior.
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.