Security audit
🔗 SKILL联动协调器
Security checks across malware telemetry and agentic risk
Overview
This skill coherently coordinates learning-related skills and discloses limits around consent, minimal data use, writebacks, and reminders.
Before installing, confirm you are comfortable with a coordinator skill using authorized summaries from multiple learning skills and writing back study-profile or reminder updates only when you explicitly allow it. The reviewed artifacts do not show hidden commands, credential use, destructive actions, or undisclosed data export.
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.