ClawHub
Back to skill

Security audit

Starloop

Security checks for vulnerabilities and agentic risk

Overview

This skill reads a user-provided todo folder, ranks tasks, and may run a disclosed ClawHub search for missing capabilities.

Install only if you are comfortable giving the agent read access to the todo folder you provide. The optional ClawHub search step is disclosed and appears read-only, but it may invoke an external `bunx` command to look up possible skills.

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.