ClawHub
Back to skill

Security audit

System Design

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only system design guide with no commands, data access, persistence, or hidden behavior.

Installers should understand that the skill may be offered for a broad range of system design or architecture conversations, but the reviewed artifact is only advisory markdown and does not run code or access user data.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The listed trigger conditions go beyond specific example phrases and include broad contexts like 'Greenfield service, major scale milestone, multi-region, or realtime needs.' These conditions are not tightly scoped and could overlap with many ordinary engineering discussions, making it unclear when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.