Security audit
党政公文格式化
Security checks across malware telemetry and agentic risk
Overview
The submitted skill artifacts expose operational helper workflows and service API scripts, but the sensitive capabilities are visible, purpose-aligned, and not hidden or automatically executed at install time.
Install only if you intend to let the agent assist with operational systems. Review configured tokens and org memory settings first, use least-privilege service credentials, and be cautious before running scripts that create, update, delete, deploy, push, or share incident knowledge.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.