Work Productivity Ontology Typed Workflow Helper

• Outcome: Pass
• Latest audit: Jun 20, 2026 at 3:33 PM UTC
• Version:
  0.1.0

Overview

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

Installation is reasonable if you want a general workflow helper for ontology-style or typed knowledge-graph tasks. Be aware it may activate for broad terms like knowledge, graph, memory, creating, or bug fix, so users may need to explicitly choose a more specific skill when working outside that domain.

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 (10)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger sentences are very generic and match common user requests such as 'help me' or 'I need a practical workflow,' which can cause the skill to activate in contexts the user did not intend. In an agent ecosystem, over-broad activation increases the chance of prompt routing mistakes, unintended execution, and interference with more appropriate skills, especially because this skill claims broad workflow and implementation support.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger phrases are broad, generic, and closely resemble ordinary user requests, which can cause the skill to activate unintentionally in unrelated contexts. This creates routing ambiguity and may lead to unexpected execution of the skill's workflow, reducing user control and potentially exposing downstream systems to unnecessary processing or unsafe assumptions.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The skill description is broad enough to match many ordinary productivity, workflow, and implementation requests, which can cause the agent to invoke this skill outside its intended scope. Over-broad activation increases the chance of prompt-space interference, incorrect routing, and unintended authority being given to this skill in unrelated tasks.

Vague Triggers

Medium

• Confidence: 98% confidence
• Finding: The keyword triggers include highly generic terms such as 'knowledge', 'graph', 'structured', 'memory', 'creating', and 'bug fix', all of which commonly appear in unrelated user requests. This makes accidental activation likely and can lead to inappropriate skill selection, degraded safety boundaries, and confusion about which instructions should control the response.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The example trigger phrases are written in vague, everyday language and effectively encourage activation from ordinary requests for help or workflows. Because examples often shape downstream routing behavior, these broad phrases materially raise the risk that the skill will be selected for loosely related prompts and inject irrelevant instructions into conversations.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger keywords are broad and overlap with common terms like 'knowledge', 'graph', 'structured', and 'creating', which can cause the skill to activate for unrelated user requests. In an agent-routing context, this increases the chance of mis-selection, leading to incorrect guidance, user confusion, or unsafe automation being applied in the wrong context.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The applicability description is overly broad and says to use the skill whenever users ask for several generic domains or need almost any practical workflow, checklist, analysis, or implementation support. This ambiguity can cause over-invocation, where the agent selects this skill for tasks outside its intended scope, reducing reliability and potentially bypassing more appropriate specialized skills.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default prompt contains a very broad activation phrase built from common words like work, productivity, workflow, analysis, and implementation support, which can match many unrelated user requests. In systems that support prompt-based routing or invocation, this can cause accidental skill activation and expose users to behavior they did not explicitly request, increasing the chance of misrouting, prompt interference, or unintended tool use.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: Enabling implicit invocation without strong activation constraints allows the platform to auto-select this skill based on ambiguous user language rather than clear intent. Because the skill description and prompt are themselves broad, the combination materially raises the risk of unintended invocation, inappropriate context capture, and execution of a workflow helper in conversations where the user did not mean to call it.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger sentences are broad natural-language phrases that resemble common user requests rather than narrowly scoped invocation patterns. This can cause unintended activation of the skill in unrelated conversations, leading the agent to apply the wrong workflow, produce off-target outputs, or override a more appropriate skill selection path.

VirusTotal

63/63 vendors flagged this skill as clean.