Jira
Security checks across malware telemetry and agentic risk
Overview
The available evidence shows a coherent, disclosed skill with clean scanner telemetry and no artifact-backed malicious behavior.
Install this only in a workspace where you trust the publisher and the local CLI credentials available to your agent. Review any authenticated or state-changing command before letting the agent run it, especially moderation, publishing, or repository maintenance actions.
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.