ClawHub
Back to skill

Security audit

prompt-architect

Security checks for vulnerabilities and agentic risk

Overview

This prompt-design skill is broad and opinionated, but it is a single Markdown instruction file with no code execution, data access, persistence, or hidden install behavior.

Install this if you want a structured prompt and AI workflow design assistant. Expect it to ask clarifying questions before drafting and to default to Chinese unless you specify another language; consider narrowing or disabling it if the broad trigger interrupts simple AI-related questions.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata and frontmatter instruct the agent to use this skill for an extremely broad set of AI-related requests and even says to 'always use this skill' for seemingly simple requests. This can override normal skill-routing discretion, causing unnecessary interception of unrelated tasks, prompt hijacking of the interaction flow, and reduced adherence to user intent or safer/more appropriate tools.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction '默认中文输出，除非用户切换语言' forces a default language choice without confirming the user's preference. This can degrade usability, mis-handle multilingual or English-only contexts, and create unsafe misunderstandings when precise language matters, especially in technical or compliance-sensitive prompt design tasks.

Content

No source excerpt is available for this finding.