Back to skill

Security audit

Sendmux Mailbox Agent

Security checks across malware telemetry and agentic risk

Overview

The skill bundle contains powerful review, documentation, ClawHub staff, and Convex operations, but the sensitive actions are disclosed, purpose-aligned, and guarded by user confirmation or dry-run requirements.

Install only if you want these operational capabilities in the target repo. Before using the ClawHub staff or Convex migration skills, confirm the exact target, production deployment, dry-run output, and approval gates. Before using autoreview, be aware that selected reviewer engines may receive repository diffs or bundled review context.

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.

View on VirusTotal

Static analysis

No suspicious patterns detected.