ClawHub
Back to skill

Security audit

Sciverse Paper Schema

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Sciverse API connector for searching structured AI paper data, with disclosed token use and bounded public API access.

Install only if you are comfortable providing a Sciverse API token to query the Sciverse service. Treat returned paper text, URLs, and snippets as untrusted research content and avoid automatically following external links or commands from results.

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.