ClawHub
Back to skill

Security audit

NanoBanana电商图片生成提示词工程

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-writing guide for e-commerce image generation and does not request tool access, credentials, persistence, or code execution.

Installers should treat this as a content/prompting aid. Users who need Chinese or other non-English text in product images may need to adapt the guidance or add text in post-production, but no sensitive permissions are requested by the skill itself.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The document states that rendered text should be limited to short English words and tells users not to render non-English text such as Chinese characters. This imposes a language constraint in the skill guidance without presenting it as an optional limitation, user choice, or clearly justified region-specific requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.