Work Productivity Nano Banana Workflow Helper

• Outcome: Pass
• Latest audit: Jul 9, 2026 · 5:51 AM UTC
• Version: 0.20260702.35207

Overview

The skill appears non-malicious, but its activation wording is broad enough that it could be invoked for unrelated requests.

Before installing, review the activation phrases and consider narrowing or disabling implicit invocation if your agent supports that. The main risk is accidental use on unrelated tasks, not malware or hidden data access based on the available evidence.

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 (9)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger keywords and example activation phrases are extremely broad (e.g. common terms like 'nano', 'banana', 'pro', 'generate', 'edit', 'bug fix'), which can cause accidental or inappropriate invocation of the skill outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user requests into this skill, leading to confusion, unsafe workflow substitution, and reduced reliability of downstream actions.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger keywords and example invocations are very broad, including generic terms like "nano", "banana", "pro", "generate", "edit", and "bug fix". This can cause the skill to activate for unrelated user requests, leading to unintended prompt/context injection into conversations and making the agent apply this workflow outside its intended scope.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger list includes extremely generic terms such as "nano", "banana", and especially "pro", plus broad action words like "generate" and "edit". This can cause unintended activation for unrelated user requests, leading the agent to invoke this skill outside its intended scope and potentially override more appropriate or safer skills.

Vague Triggers

High

• Confidence: 90% confidence
• Finding: The manifest description says to use the skill when a user asks for broad categories like "work-productivity" or needs a "practical workflow, artifact, checklist, analysis, or implementation support," which are highly ambiguous and cover many normal requests. This increases the chance of overbroad invocation, misrouting, and unintended interception of user tasks that are not actually related to this skill's specialized purpose.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger list includes extremely broad, common terms such as "nano", "banana", and "pro", which can cause the skill to activate for many unrelated requests. This creates prompt-routing confusion and may lead to unintended execution of the skill in contexts where its workflow, assumptions, or generated artifacts are inappropriate.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The description says to use the skill when users mention broad categories or need generic workflow artifacts, analysis, or implementation help, but it does not clearly define exclusion criteria or precise routing conditions. This ambiguity increases the chance of accidental invocation and overlap with unrelated skills, reducing reliability and potentially exposing users to incorrect task handling.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill enables implicit invocation while advertising a very broad, loosely bounded purpose through generic keywords like work-productivity, workflow, checklist, analysis, and implementation support. This increases the chance the agent will auto-select the skill in contexts the user did not clearly intend, which can cause prompt-scope confusion, unintended delegation, or misuse of the skill in adjacent tasks.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence begins with a very broad phrase ('Help me') tied to a long requirement description, which can cause the skill to activate during ordinary user requests that were not meant to invoke it. In an agent ecosystem, overly broad activation increases the chance of unintended routing, context hijacking, and execution of the wrong workflow, especially because the skill is framed as a general practical helper across multiple adjacent tasks.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger sentence ('I need a practical workflow for ...') is ambiguous because it describes a common user intent rather than a specific activation condition. This makes accidental invocation likely across many unrelated productivity requests, which can misroute user tasks and expand the skill's effective scope beyond what the author likely intended.

VirusTotal

59/59 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.