ClawHub
Back to skill

Security audit

败家子

Security checks for vulnerabilities and agentic risk

Overview

This skill only generates intentionally long answers after explicit confirmation and does not request file, network, credential, or persistence access.

Install only if you actually want a skill that can spend tokens producing deliberately expanded output. It is clearly opt-in and bounded, but users should remember that confirmed use may consume time or token budget by design.

SkillSpector

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

Static analysis

No suspicious patterns detected.