Security audit

Work Productivity Self Improving Workflow Helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only workflow helper with broad activation wording, but it does not request sensitive access, persistence, credentials, or hidden execution.

Before installing, be aware this skill may activate on generic productivity or bug-fix wording. It appears safe as a workflow helper, but maintainers should narrow the trigger phrases to explicit self-improving-agent workflow requests.

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 (10)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The keyword list includes very broad terms such as "self" and "improving," which are common in ordinary conversation and can cause unintended skill activation. In an agent environment, this increases the chance the skill is invoked outside the user's intent, potentially steering workflows, generating irrelevant actions, or interfering with other skills.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger sentences are loosely phrased and based on everyday language like "Help me" and "I need a practical workflow," which can match many unrelated requests. This makes accidental or overbroad activation more likely, especially in multi-skill systems where ambiguous prompts can route control to the wrong skill and affect agent behavior.

Vague Triggers

High

Confidence: 93% confidence
Finding: The trigger phrases include extremely generic terms such as "self", "improving", and broad help-style prompts that can match many unrelated user requests. This can cause the skill to activate unexpectedly, increasing the chance of inappropriate routing, prompt-context interference, or unintended execution in situations where the user did not actually request this workflow helper.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger list includes extremely generic terms such as "self" and "improving," which are common in ordinary conversation and can cause the skill to activate far outside its intended scope. This increases the chance of unintended routing, prompt hijacking of unrelated tasks, and accidental exposure of the skill's instructions in contexts where it was not meant to run.

Vague Triggers

High

Confidence: 89% confidence
Finding: The description says to use the skill when a user asks for broad concepts like "self," "improving," or "practical workflow," without defining firm boundaries. Ambiguous activation guidance makes misrouting more likely and can cause this skill to intercept requests unrelated to the intended domain, degrading safety and reliability of orchestration.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The example triggers model broad natural-language prompts instead of bounded invocation patterns, teaching downstream systems that vague wording is sufficient to activate the skill. This reinforces accidental activation behavior and makes it harder to distinguish intentional use from ordinary user conversation.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger keyword list includes extremely broad terms such as “self”, “improving”, “enable”, and “bug fix”, which are common in unrelated user requests. This can cause the skill to activate outside its intended scope, leading to incorrect routing, irrelevant guidance, or unintended influence over conversations that did not request this workflow helper.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The description says to use the skill when users mention broad concepts like work-productivity, self, improving, or ask for practical workflow support, but it does not clearly define boundaries for when the skill should not apply. This ambiguity increases accidental invocation risk and can cause the skill to handle requests better suited for other skills or general assistant behavior.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The default prompt is overly broad and can cause the skill to be invoked in situations that only loosely match the described topic. Because implicit invocation is enabled, this increases the chance of accidental routing, prompt confusion, or unintended use of the skill in contexts where its behavior was not explicitly requested.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger sentences and keywords include broad, common-language terms such as "help me," "I need," "self," and "improving," which can cause the skill to activate in contexts far outside its intended scope. In an agent system, this increases the chance of unintended invocation, misrouting user requests, and injecting this skill into unrelated workflows where it may override more appropriate handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.