ClawHub
Back to skill

Security audit

Prompt Quality Checklist

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only prompt quality checklist for AI image/video storyboard prompts, with no code execution, credential access, persistence, or hidden data handling.

Install only if you want a Chinese-language checklist for reviewing AI short-film or storyboard generation prompts. Expect strict prompt-quality feedback and asset-path conventions; no local data or credentials are needed for its stated use.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger list includes broad, everyday phrases such as '检查清单', '质量审核', '自查', and '自审', which can plausibly appear in many unrelated conversations. This increases the chance of accidental invocation, causing the skill to activate outside its intended prompt-audit context and potentially interfere with normal workflows or override user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The document title and all operational instructions are written in Chinese, which effectively imposes a single language for using the skill materials. The file does not indicate that language choice is optional, nor does it justify a region-specific requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.