Security audit
Plisio
Security checks across malware telemetry and agentic risk
Overview
The available skill files appear to be disclosed development and moderation helpers, with no evidence of hidden data collection or destructive behavior.
Review the high-impact workflows before installing: moderation commands can change user and skill state, migrations can alter production data, UI proof can publish PR artifacts, and autoreview can invoke a full-access nested review mode unless run with its opt-out. These behaviors are disclosed and should be used only in the intended repos with appropriate credentials and confirmation.
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.