Security audit
entropy-intimate-therapy
Security checks across malware telemetry and agentic risk
Overview
The visible skills are clear workflow guides with disclosed command use and no evidence of hidden data theft, persistence, or destructive automation.
Install only if you expect these skills to run developer and maintainer workflows in a ClawHub/Convex repo. Review the autoreview helper before use if you do not want nested Codex review running with full sandbox bypass, and use the documented opt-out for lower privilege.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.