Security audit
i0e
Security checks across malware telemetry and agentic risk
Overview
This is a simple planning-protocol skill that does not request external access, persistence, credentials, or code execution.
This skill appears safe to install as a lightweight planning aid. Users should understand that it may guide an agent to break a broad request into subtasks, but any powerful actions would come from the user’s original goal and the agent’s available tools, not from hidden behavior in this skill.
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.