Security audit
Self Improving Agent
Security checks across malware telemetry and agentic risk
Overview
This skill is a simple disclosed local learning log for the agent, with no install scripts, executables, network requirements, or hidden behavior found.
Install only if you want your agent to keep a small local memory across sessions. Avoid letting it record secrets or sensitive project details in the log, and review or delete ~/.agent-learn/log.md if you no longer want that memory retained.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.