Back to skill

Security audit

NanobananaPro 生图大师

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only NanobananaPro prompt helper with no code execution, dependencies, persistence, or credential handling, though its activation terms are broad.

Install only if you want a Chinese-language NanobananaPro prompt-writing helper. Be aware that generic trigger words may activate it during unrelated image, prompt, or video-generation conversations; review generated prompts before using them on any external platform.

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
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 (11)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes generic everyday terms such as 'prompt', '生图', '做图', and '视频生成', which are likely to appear in ordinary user conversations unrelated to explicitly invoking this skill. That can cause unintended activation, misrouting user requests, and prompt/context hijacking of normal interactions, especially because multiple aliases are short and broad.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The entire skill description, examples, and usage guidance are presented only in Chinese, with no indication that users may choose another language or that the skill is intentionally region-specific. Under the stated policy, imposing a single language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill is written entirely as a Chinese-first workflow and does not provide a user language-selection mechanism or an explicit opt-in for output language. This can cause the agent to respond in an unexpected language, reducing user comprehension and increasing the chance that users copy prompts or settings they do not understand.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The scene trigger list includes very broad everyday phrases such as '帮我生成一个...' and '怎么写提示词...', which can cause the skill to activate outside the intended NanobananaPro-specific context. Over-broad activation can hijack unrelated user requests, route conversations into the wrong skill, and create unsafe or misleading behavior by suppressing more appropriate handlers.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document title and usage framing are entirely in Chinese, and there is no indication that users may choose another language or that the Chinese-only presentation is required for a region-specific purpose. Under the policy, forcing a specific language without opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill reference is written exclusively in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in can constitute a natural-language policy violation unless the locale restriction is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire template, headings, instructions, examples, and output structure are written only in Chinese, with no indication that users may choose another language. This creates a natural-language locale constraint that is not documented as optional or region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown file presents all usage guidance and style instructions in Chinese, with only partial English glosses for style labels. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is excessively broad and includes generic terms such as 'prompt', '生图', 'AI 绘画', '镜头', and '视频生成', which are likely to overlap with many unrelated user requests. This can cause the skill to activate unexpectedly, hijack routing from more appropriate skills, and increase exposure to any unsafe prompt-generation behavior embedded in the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description forces a specific language/locale in user-facing metadata, which can violate language-choice policy when no opt-in or justification is provided. There is no indication that the skill is region-specific or that alternative language support is available.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The display name and description are written entirely in Chinese, with no indication that the skill is region-specific or that users can choose another language. This creates a natural-language locale constraint in the skill metadata without documented justification or opt-in.

Content

No source excerpt is available for this finding.