Back to skill

Security audit

周报生成器

Security checks across malware telemetry and agentic risk

Overview

The reviewed skill artifacts are purpose-aligned operational and development helpers with clear guardrails and no evidence of hidden exfiltration, persistence, or destructive behavior outside user-directed workflows.

Install only in an environment where the operator is expected to perform ClawHub staff or Convex maintenance tasks. Review the admin and migration skills carefully before use because they can affect real users, emails, packages, and production data when run with valid credentials.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.