Second Brain Growth
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed second-brain audit helper that reads a local Hbrain knowledge base and can produce reports, without hidden code, exfiltration, or automatic privileged behavior.
Install only if you want an agent to inspect your local Hbrain/llm-wiki knowledge base. Review the hard-coded paths before use, and only approve Hermes cron setup or saved reports when you are comfortable with scheduled recurring analysis and report files being written under the documented _meta directories.
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.