Security audit
Skill Experience Layer
Security checks across malware telemetry and agentic risk
Overview
This skill is instruction-only, but it asks the agent to keep persistent lessons that can steer future commands, messages, scheduling, and Feishu/Lark actions without clear user control.
Install only if you intentionally want persistent experience files to influence future agent behavior. Review every JSON file before use, remove the Feishu/Lark open_id and local paths, keep entries project-specific where possible, and require explicit confirmation before applying stored lessons to shell commands, messaging, cron jobs, skill management, or external-account 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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.