Security audit

NanoBanana E-commerce Image Generation Prompt Engineering

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static prompt-writing guide for e-commerce image generation and does not request access, run code, persist data, or hide behavior.

This skill appears safe to install as a prompt reference. Users creating non-English packaging or long label copy should treat the English-only text advice as a practical model limitation and adapt the workflow as needed, such as by adding final text in post-production.

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
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
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: Line L050 explicitly says to limit rendered text to short English words and to avoid rendering complex non-English characters directly. This is a natural-language language policy constraint that disfavors non-English usage without an opt-in or clear region-specific justification.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.