Security audit
Encoding & Formats
Security checks across malware telemetry and agentic risk
Overview
The skill is mostly a coherent encoding reference, but its auto-decode script contains an unsafe input-handling pattern that could run code from a crafted string.
Review this skill before installing. Its reference commands are generally normal for encoding work, but do not use the provided Quick Decode Script on untrusted input unless the URL-decoding line is rewritten to pass input via stdin or argv instead of embedding it in Python code. Also avoid pasting real JWTs or secrets unless you trust the environment.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.