Security audit
Second Brain Ai
Security checks across malware telemetry and agentic risk
Overview
This skill coherently provides local Markdown note search and controlled note-writing within a user-configured vault.
Install only if you are comfortable letting the agent read snippets from the Markdown vault you set in SECOND_BRAIN_VAULT. Point it at a narrow notes folder, use .secondbrainignore for sensitive areas, and require explicit confirmation before allowing capture_note, append_note, or init_vault writes.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.