Back to skill

Security audit

Changelog Generator Zh

Security checks across malware telemetry and agentic risk

Overview

The skills are mostly coherent and disclosed, but one review helper defaults to running a nested agent with full filesystem access and approval bypass, which deserves careful review before installation.

Install only if you trust the publisher and need these ClawHub maintainer workflows. Before using autoreview, prefer `--no-yolo` or set the equivalent environment override unless you intentionally want a nested review agent to bypass approvals with full filesystem access. Treat moderation and PR-publishing commands as high-impact and verify targets before confirming writes.

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.

View on VirusTotal

Static analysis

No suspicious patterns detected.