Security audit
Leetspeak Decoder
Security checks across malware telemetry and agentic risk
Overview
This skill is a small offline leetspeak decoder whose behavior matches its stated purpose and shows no evidence of hidden network, credential, persistence, or destructive activity.
Reasonable to install for offline decoding and safety triage. Treat any decoded message as untrusted text, especially if it appears to contain commands, secrets, or prompt-injection language.
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.