Security audit
anything-to-skill
Security checks across malware telemetry and agentic risk
Overview
This skill gives a clear, purpose-aligned workflow for turning user-provided documents into reusable agent skills, with appropriate cautions about extraction quality and untrusted source text.
Before installing or using it, make sure you trust the anything-to-skill CLI source and review generated skills before relying on them, especially when source documents are private, copyrighted, scanned, or may contain prompt-injection text.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.