Security audit
Therapy
Security checks across malware telemetry and agentic risk
Overview
This is a simple mental-health support prompt that asks for expected user-provided mood information and does not include code, credentials, hidden access, or external data sharing.
Reasonable to install from an agentic-security perspective. Treat it as a self-awareness and therapy-preparation aid, not clinical care; avoid sharing unnecessary identifying details, and seek professional or emergency help in crisis situations.
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.