Work Productivity Nano Banana Workflow Helper

• Outcome: Review
• Latest audit: Jul 24, 2026 · 5:08 PM UTC
• Version: 0.1.0

Overview

This skill is not destructive, but it should be reviewed because it allows automatic activation with very broad triggers that could steer unrelated user requests.

Review or narrow this skill before installing. It appears documentation-only, but disable implicit invocation or replace the generic keywords with specific Nano Banana Pro workflow phrases so it does not activate during unrelated image, coding, workflow, or bug-fix requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger phrase is broad enough to match common user language such as generic requests for help, workflows, or implementation support. In an agent skill system, this can cause unintended invocation, leading the skill to intercept prompts outside its intended scope and potentially override or distort task routing.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The activation guidance mixes broad keywords like 'nano', 'banana', 'pro', 'generate', and 'bug fix' with vague example prompts, making the skill boundary unclear. This increases the chance of accidental activation on unrelated everyday requests, which can create prompt-routing confusion and reduce reliability of the overall agent system.

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The trigger keywords and sample invocations are excessively broad, including generic terms like 'nano', 'pro', 'generate', 'edit', 'images', and 'bug fix'. This can cause the skill to activate in unrelated contexts, leading to unintended routing, incorrect workflow execution, or accidental handling of user requests outside the skill's intended scope.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes extremely generic terms such as "nano," "banana," "pro," and "generate," which are likely to appear in many unrelated requests. This can cause unintended activation of the skill outside its intended domain, leading to prompt-routing confusion, incorrect tool use, or accidental exposure of users to irrelevant workflow instructions.

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The manifest description says to use the skill when a user asks for broad concepts like "practical workflow," "artifact," "checklist," or "analysis," which are common across many tasks. This creates an overly permissive activation boundary and increases the chance the skill is selected for unrelated requests, degrading agent reliability and potentially interfering with safer or more appropriate skills.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The example trigger sentences are vague and largely repeat broad requirement text instead of showing concrete, bounded invocation cases. In practice, this trains routing systems or maintainers toward expansive interpretation, making accidental invocation more likely and reducing confidence that the skill will only run in the intended context.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger list includes extremely generic terms such as "nano", "banana", "pro", "generate", and "edit", which are likely to appear in many unrelated prompts. This can cause the skill to activate outside its intended scope, leading to prompt hijacking of unrelated tasks and unpredictable behavior in agent routing.

Vague Triggers

High

• Confidence: 91% confidence
• Finding: The description says the skill should be used when users mention broad terms or need generic artifacts like workflows, checklists, analysis, or implementation support, which creates an overly expansive invocation scope. In an agent system, this broad matching can make the skill intercept requests it was not designed for, reducing reliability and potentially overriding safer or more appropriate skills.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The example trigger phrases are truncated and malformed, so they do not clearly communicate what should or should not activate the skill. Ambiguous examples increase the chance that downstream systems or maintainers will implement overly permissive matching, compounding accidental activation risk.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The manifest enables implicit invocation via `allow_implicit_invocation: true` without any narrowly defined activation constraints in the file. That can cause the skill to be auto-selected in broader contexts than intended, increasing the chance it is invoked on unrelated user requests and gains access to conversations or tasks it should not influence.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence begins with a very broad everyday help-request pattern, which can cause the skill to activate for many unrelated user prompts. Overbroad activation increases the chance of prompt/skill hijacking, accidental routing, and inappropriate use of this workflow in contexts the author did not intend.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: This trigger uses a broad generic request pattern ('I need a practical workflow for ...'), making the skill eligible for activation from commonplace language rather than a clearly bounded task signature. That can lead to unintended invocation, reduced routing precision, and a larger attack surface for malicious or irrelevant prompts to reach the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.