ClawHub
Back to skill

Security audit

ai-architecture-harness-en

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only architecture guardrail guide with no hidden execution, network access, credential handling, or persistence outside project documentation and tests.

Before installing, understand that this skill may encourage creating or updating architecture guardrail docs and tests in repositories. It is most useful for larger or long-running AI-assisted coding work, and users should keep those documentation changes reviewed and scoped to the project.

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
91% confidence
Finding

The skill description contains multiple broad trigger phrases such as 'AI coding', 'Agent coding', and 'wants the codebase to be safer for AI Agent modifications', which can cause the skill to activate for many generic software-engineering requests outside its narrowly intended purpose. Overbroad activation increases the chance that an agent applies this skill in irrelevant contexts, potentially introducing unnecessary documentation changes, process overhead, or architecture-directed edits that distract from the user's actual task.

Content

No source excerpt is available for this finding.