Work Productivity Proactive Agent Workflow Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 7:51 AM UTC
• Version: 0.20260729.110214

Overview

This is a documentation-style workflow helper with overly broad auto-activation wording, but it does not show hidden execution, data access, persistence, or destructive behavior.

Install only if you want a general proactive-agent workflow helper, and consider tightening or disabling implicit invocation so it does not activate on ordinary task or productivity 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 (10)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger phrases are broad and partially generic, including common terms like 'task', 'transform', and 'proactive', which can cause the skill to activate in contexts far beyond its intended scope. In an agent system, overbroad activation increases the chance of unintended invocation, workflow hijacking, or conflicting behavior with other skills, reducing reliability and potentially steering sensitive tasks through the wrong automation path.

Vague Triggers

High

• Confidence: 91% confidence
• Finding: The trigger phrases are broad, generic, and partially include natural-language fragments that could match unrelated user requests, increasing the chance of accidental activation. In a proactive workflow skill, unintended invocation can cause the agent to apply the wrong workflow, produce irrelevant artifacts, or interfere with safer skill-routing and user intent handling.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger list includes very generic terms such as "proactive," "task," "needs," and "bug fix," which are common in ordinary conversations and can cause the skill to activate outside its intended scope. Overbroad activation increases the chance of incorrect routing, unintended instruction injection from unrelated contexts, and user confusion about why this skill was selected.

Vague Triggers

High

• Confidence: 91% confidence
• Finding: The manifest description uses broad matching language like "Use when a user asks for work-productivity, proactive-agent, proactive, transform, task," which can match many unrelated requests. This makes the skill prone to accidental invocation and scope creep, especially in systems that rely on description text for routing or tool selection.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger list includes very generic terms such as "proactive," "task," "needs," and "bug fix," which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that this skill intercepts requests outside its intended scope, leading to unintended behavior, user confusion, or unsafe delegation to an ill-matched workflow.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The invocation description says to use the skill for broad categories like work-productivity, proactive-agent, proactive, transform, and task, plus any need for practical workflows or analysis around the requirement. This lacks clear boundaries, so the system may route many loosely related prompts to the skill, increasing the risk of inappropriate activation and unreliable outputs.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill metadata uses broad, generic activation language in both the description and default prompt, making it likely to trigger for loosely related user requests. This can cause unintended routing to the skill, increasing the chance that users receive actions, workflow suggestions, or transformations they did not explicitly request.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: Implicit invocation is enabled even though the skill's activation language is broad and weakly constrained. In that combination, the platform may auto-select this skill for many unrelated prompts, creating a high risk of unauthorized or confusing intervention in user workflows.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger sentence begins with a very broad everyday help request, making it likely to activate in many unrelated conversations. In an agent-routing context, overbroad activation can cause the wrong skill to take control, leading to irrelevant guidance, missed user intent, or unsafe workflow substitution.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: This trigger is too vague about the conditions under which the skill should activate, so ordinary requests for a 'practical workflow' could match even when the user is asking for something unrelated. Ambiguous activation logic increases the chance of unintended invocation and confused task execution in multi-skill environments.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.