ClawHub
Back to skill

Security audit

Dualgap

Security checks for vulnerabilities and agentic risk

Overview

DualGap is a coherent research-analysis skill that reads user-selected PDF folders, calls a user-configured LLM API, and writes local research outputs without hidden persistence or unrelated access.

Before installing, confirm you are comfortable sending extracted PDF text and research notes to the configured LLM provider. Keep API keys in a local env/config file outside generated outputs, and use the smoke-test limits first if cost or data exposure is a concern.

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.