Security audit
Self-Improving Proactive Agent
Security checks across malware telemetry and agentic risk
Overview
This markdown-only skill keeps disclosed local memory and task-state files to help an agent remember preferences and follow up, with clear limits on sensitive actions.
Install this if you want an agent to keep local preference, correction, and task-state notes across sessions. Review the ~/self-improving/ and ~/proactivity/ files periodically, avoid putting secrets there, and approve any edits to workspace steering files before relying on them.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.