Work Productivity Pollyreach Gives Workflow Helper

• Outcome: Pass
• Latest audit: Jul 28, 2026 · 11:22 AM UTC
• Version: 0.20260728.90410

Overview

This is a documentation-only workflow helper with overly broad activation wording but no hidden execution, data access, persistence, or credential handling.

Installers should be aware that this skill may be selected too often because of broad trigger words like common workflow and productivity language. It is otherwise low-risk: review outputs for relevance, and prefer explicit invocation when using it.

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

High

• Confidence: 95% confidence
• Finding: The trigger phrases are generic enough to match ordinary conversation such as requests for help, workflows, bug fixes, or productivity support. This can cause the skill to activate unintentionally, increasing the chance that unrelated user requests are routed through this skill and inherit its instructions or behaviors without clear user intent.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger phrases are broad and generic enough to match ordinary user requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the chance of prompt hijacking of unrelated tasks, unintended workflow execution, and confusing or unsafe automation behavior.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes extremely generic words such as "every," "phone," "number," "ability," "things," and "done," which can match ordinary user requests unrelated to this skill. That can cause unintended activation, leading the agent to apply the wrong workflow, override more appropriate skills, or inject irrelevant instructions into benign conversations.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The example trigger phrases are broad templates like "Help me..." and "I need a practical workflow for..." that resemble normal user requests and do not clearly distinguish when this skill should activate. In systems that use examples for routing or similarity matching, this can significantly widen activation scope and cause accidental invocation in unrelated contexts.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keyword list includes extremely broad everyday terms such as "every", "phone", "number", "ability", "things", and "done", which can cause the skill to activate in many unrelated conversations. Over-broad activation can route user requests into the wrong workflow, producing unintended actions, irrelevant guidance, or unsafe context mixing in agent pipelines.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill description defines enablement conditions too broadly, including general requests for practical workflows, artifacts, checklists, analysis, or implementation support around loosely related terms. This weak boundary definition increases the chance of accidental invocation and misclassification, especially in automated agent environments where routing decisions may rely heavily on the description.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The default prompt contains a very broad natural-language trigger phrase and the policy explicitly allows implicit invocation, which increases the chance this skill is activated during ordinary user conversations without clear intent. That can cause unintended routing to this skill, exposing users to unexpected behavior, irrelevant actions, or prompt/context injection pathways from a skill they did not mean to invoke.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence is built from broad, everyday terms and a truncated generic request pattern, which can cause the skill to activate for unrelated user requests. In an agent environment, unintended invocation can misroute tasks, override more appropriate skills, and create confusing or unsafe workflow execution without the user's informed intent.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger guidance does not clearly state when the skill should and should not activate, leaving broad room for interpretation by routing logic or downstream agents. This ambiguity increases the chance of accidental activation, task hijacking, and inconsistent behavior, especially because the skill targets generic productivity-style requests that overlap with many benign workflows.

VirusTotal

62/62 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.