ClawHub
Back to skill

Security audit

Svix

Security checks for vulnerabilities and agentic risk

Overview

The skill bundle is coherent for ClawHub and Convex maintainer workflows, with high-impact commands disclosed and mostly user-directed.

Install only in a ClawHub maintainer environment where you are comfortable with repository tooling, GitHub CLI access, Convex commands, and audited moderation workflows. Before using autoreview, consider whether to pass --no-yolo or disable fallback reviewers if you do not want full-access nested review or diff sharing with external AI CLIs.

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.