ClawHub
Back to skill

Security audit

architect-project-state

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped project-state helper that records architectural decisions and evidence without hidden execution, credential use, or unrelated access.

Before installing, confirm that users understand it will create project-state and change-log files inside a chosen project root. Its safeguards are appropriate for architectural recordkeeping, but human review remains necessary for client commitments, statutory conclusions, and professional judgments.

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.