Security audit
LyraShield AI
Security checks across malware telemetry and agentic risk
Overview
This is a small LyraShield review helper that discloses its OAuth MCP use and limits write actions behind explicit approval.
Before installing, confirm you trust the LyraShield MCP connection and only grant the OAuth scopes you need; keep write access limited because it requires stronger authority even though this skill asks for explicit approval before writes.
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.