ClawHub
Back to skill

Security audit

Architecture Review

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed architecture review of a codebase and writes a local HTML report, with no evidence of hidden execution, credential access, exfiltration, or destructive behavior.

Before installing or using it, run it only on repositories you intend to review, give an explicit project path or scope, and remember that the generated HTML report may summarize private code structure and technical debt.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation example uses a very broad natural-language trigger ('help me analyze the architecture of project XX') without defining scope, repository boundaries, or output constraints. This can cause the agent to activate unexpectedly on generic requests and then perform expansive repository scanning and report generation, increasing the chance of unintended data exposure or over-collection in environments containing sensitive code or metadata.

Static analysis

No suspicious patterns detected.