Security audit
Use when a session reveals stable user preferences, workflow corrections, or project conventions that should be preserved for future sessions. Also use when user explicitly asks to remember rules, update guidance, or summarize learnings.
Security checks across malware telemetry and agentic risk
Overview
This skill is an instruction-only helper for saving stable user and project preferences, with its persistent CLAUDE.md edits disclosed and normally gated by confirmation.
Install this if you want an agent to preserve stable preferences and project conventions across sessions. Review proposed CLAUDE.md changes before accepting them, and be cautious with automatic end-of-session learning because mistaken or overly broad preferences could persist.
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.
Static analysis
No suspicious patterns detected.