Security audit

Work Productivity Self Improving Workflow Helper

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk workflow helper with overly broad activation wording but no hidden execution, data access, persistence, or destructive behavior.

Before installing, be aware that this skill may activate on generic words related to self-improvement or productivity. It appears safe as a guidance-only helper, but users may prefer narrower trigger wording or explicit invocation to avoid irrelevant responses.

SkillSpector

By NVIDIA

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 (9)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger examples use broad natural-language phrasing that could cause the skill to activate for generic requests unrelated to the user's explicit intent. In an agent setting, overbroad invocation increases the chance of unsolicited workflow execution, prompt hijacking through ambiguous routing, or accidental use of a powerful self-improving/proactive behavior when a narrower skill was intended.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger phrases are highly generic and include common words like "self", "improving", and "proactive", plus broad request templates. This can cause the skill to activate for unrelated user prompts, leading to unintended invocation, context hijacking, or the skill influencing workflows outside its intended scope.

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger list includes extremely broad terms like `self`, `improving`, and `proactive`, which are common in ordinary conversation and unrelated tasks. This can cause unintended skill activation, routing user requests into this skill when they did not intend to use it, increasing the chance of inappropriate workflow generation, misleading outputs, or interference with safer or more relevant skills.

Vague Triggers

High

Confidence: 94% confidence
Finding: The manifest description says to use the skill for broad categories like `work-productivity`, `self`, `improving`, and `proactive`, making invocation criteria ambiguous and overinclusive. In a skill-routing system, this can hijack many unrelated requests, causing confused deputy behavior where this skill is selected despite being only loosely relevant, which reduces safety and reliability.

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger list includes extremely broad everyday terms such as "self", "improving", and "proactive", which can match a wide range of unrelated user requests. This can cause the skill to activate unintentionally, leading to prompt-routing errors, irrelevant behavior injection, or unexpected execution of workflow guidance in contexts where it was not requested.

Vague Triggers

High

Confidence: 93% confidence
Finding: The skill description says it should be used when users ask for broad categories like work-productivity, self, improving, or proactive, without clearly defining boundaries. Ambiguous enablement criteria increase the chance of accidental invocation across many benign conversations, which can degrade system reliability and expose users to unintended instructions or outputs.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill’s invocation description and default prompt are broad and repetitive, and the policy explicitly allows implicit invocation. This combination can cause the platform to trigger the skill for loosely related user requests, leading to unintended activation and overbroad access to the skill’s behavior in contexts where the user did not clearly request it.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me ... practical help'), which can cause the skill to activate for many unrelated user requests. Overbroad activation increases the chance of accidental invocation, scope confusion, and inappropriate handling of tasks outside the skill's intended domain.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger sentence is ambiguous because it uses generic wording ('I need a practical workflow for ... practical help') without clear boundaries on what kind of workflow or task qualifies. This can misroute unrelated requests into this skill, producing incorrect outputs or causing the agent to overreach into tasks the user did not intend.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.