Work Productivity Self Improving Workflow Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:53 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with overbroad trigger wording, but it does not request sensitive access, persistence, or destructive authority.

Installers should be aware that this skill may activate too broadly because of generic trigger words. It is otherwise a low-risk guidance skill; review routing behavior if you want it to run only on explicit self-improving or proactive-agent workflow 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 (9)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger examples are extremely broad and can activate on generic words like "self," "improving," or "proactive," which are common in many unrelated user requests. In an agentic system, this can cause unintended skill invocation, leading to prompt/context injection into unrelated workflows and increasing the chance of unsafe or disruptive behavior.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger phrases include very common terms such as "self", "improving", and "proactive", plus generic request templates, which can cause the skill to activate in unrelated conversations. In an agent ecosystem, unintended invocation can route user data or control flow into the wrong skill, producing incorrect actions, confusing outputs, or unsafe autonomy escalation.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes extremely generic terms such as "self", "improving", and "proactive", which are common in ordinary user conversations and can cause unintended skill activation. In an agent environment, this can hijack routing, inject irrelevant workflow behavior, and increase the chance that this skill is invoked in contexts the user did not intend.

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The manifest description says to use the skill when a user asks for broad concepts like "self," "improving," or "proactive," which are ambiguous and likely to match many unrelated requests. This weak invocation boundary makes accidental activation more likely and can lead to inappropriate tool selection, noisy agent behavior, or opportunity for prompt-routing abuse.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger keywords are excessively broad, including generic terms like 'self', 'improving', 'proactive', and 'learning', which are likely to match ordinary user conversation unrelated to this skill. This can cause unintended activation, prompt hijacking of unrelated tasks, and inappropriate injection of the skill's workflow into normal interactions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The description uses broad 'use when' language covering many vague situations, including general requests for practical workflows, checklists, analysis, or implementation support. This ambiguity increases the chance that the skill is invoked outside its intended scope, which can override more appropriate skills or steer the agent toward irrelevant behavior.

Natural-Language Policy Violations

Medium

• Confidence: 80% confidence
• Finding: The file is a Chinese locale variant and does not appear to include any user language negotiation or opt-in behavior. If selected automatically in a mixed-language context, it could produce responses in a language the user did not request, causing confusion, degraded usability, or misinterpretation of workflow and safety guidance.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default prompt invokes the skill through a very broad phrase and the skill policy also allows implicit invocation, which increases the chance the agent will trigger this skill in contexts the user did not clearly intend. For a self-improving and proactive workflow helper, unintended activation can cause overreach into unrelated tasks, prompt-scope confusion, or unsafe autonomous assistance patterns that expand the skill's influence beyond a narrow, user-confirmed workflow.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger sentences are broad, natural phrases that overlap with ordinary user requests, which can cause the skill to activate unintentionally outside its intended scope. In an agent environment, overbroad invocation increases the chance of wrong-skill routing, prompt confusion, and unintended execution paths that may affect reliability or safety-sensitive workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.