signup-login-page-generator
Security checks across malware telemetry and agentic risk
Overview
The skill set is coherent with ClawHub development and moderation work, with sensitive actions mostly disclosed and gated by user direction.
Before installing, be aware that these skills are intended for trusted ClawHub maintainers or developers. Run moderation and publishing commands only against the intended repo/account, and use the autoreview helper's no-yolo option if you do not want nested Codex review to run with full filesystem and sandbox-bypass authority.
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.