ClawHub
Back to skill

Security audit

architecture-principles

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a disclosed architecture decision checklist without executable code, sensitive access, or persistent changes.

Use this as an opinionated architecture checklist and validate its recommendations against your project's constraints. Referenced companion skills are not bundled or assessed here.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding

Shadow Command Trigger: description clause 'Invoked by scenario-standards at its Architecture phase and consumed by workflow-orchestrator's review gates' conflicts with built-in command 'review'

Content

No source excerpt is available for this finding.