Work Productivity Pollyreach Gives Workflow Helper

• Outcome: Pass
• Latest audit: Jul 26, 2026 · 1:48 AM UTC
• Version: 0.1.0

Overview

This is a low-risk workflow guidance skill, but its trigger wording is too broad and may activate when users did not intend it.

Install only if you want a broad PollyReach-style workflow helper. The publisher should narrow triggers to explicit PollyReach or outreach-workflow phrases so ordinary requests about phones, numbers, or getting things done do not accidentally invoke 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 (11)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger keywords and example invocations are broad, generic, and loosely related terms such as 'every', 'phone', 'number', 'ability', and 'things', which can cause the skill to activate for many unrelated user requests. In an agent environment, unintended invocation can route tasks to the wrong workflow, producing irrelevant actions, confusing outputs, or accidental execution of productivity flows when the user did not intend to use this skill.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger phrases include extremely generic terms such as 'every', 'phone', 'number', 'ability', 'things', and 'done', which can match ordinary user conversation unrelated to this skill. That creates an overbroad activation surface where the skill may be invoked unintentionally, causing misrouting of user requests and increasing the chance that the agent applies the wrong workflow or exposes unrelated context to this skill.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The skill description is broad enough to match many ordinary productivity or implementation-help requests, which can cause unintended invocation outside its intended scope. Over-broad activation increases the chance that this skill will intercept requests better handled by more specific skills, creating routing confusion and potentially exposing users to irrelevant or unsafe workflow guidance.

Vague Triggers

High

• Confidence: 99% confidence
• Finding: The keyword list includes extremely vague everyday terms such as 'every,' 'phone,' 'number,' 'ability,' 'things,' and 'done,' which are likely to appear in many unrelated user prompts. This can lead to accidental triggering at high frequency, undermining skill isolation and making agent behavior unpredictable or manipulable through innocuous wording.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example triggers use generic phrasing like 'help me' and 'I need a practical workflow,' which do not establish clear activation boundaries and may train downstream systems to invoke the skill for broad classes of requests. While less severe than the keyword list itself, these examples reinforce over-triggering and increase ambiguity in routing behavior.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger keyword list includes very generic terms such as "every", "phone", "number", "ability", "things", and "done", which are common in ordinary conversation and unrelated to a narrowly scoped productivity workflow. This can cause unintended activation of the skill, leading to prompt/context injection into unrelated sessions and reducing routing integrity and user control.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The description says to use the skill when users mention broad terms like work-productivity, pollyreach, gives, every, or phone, or whenever they need a practical workflow or checklist for the requirement, but it does not clearly bound what user intents qualify. This ambiguity increases accidental invocation risk and makes it easier for the skill to activate outside its intended context.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The sample trigger phrases are broad, natural-language requests that overlap with ordinary assistance queries and repeat truncated generic text rather than a precise skill invocation pattern. These examples may train or encourage systems to match on vague conversation fragments, increasing unintended routing to this skill.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The default prompt includes a very broad natural-language trigger phrase covering common productivity terms and a long generic help request. Combined with allow_implicit_invocation: true, this increases the chance the skill is invoked during ordinary conversations where the user did not explicitly request it, which can cause unintended prompt injection surface expansion, confusing behavior, or unauthorized workflow execution within the agent context.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger guidance includes extremely broad, everyday phrasing that can match routine user language unrelated to this skill’s intended scope. This can cause over-invocation or accidental routing, leading the agent to apply the wrong workflow, produce irrelevant outputs, or bypass more appropriate skills in ambiguous contexts.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The invocation guidance lacks clear boundaries and mixes specific terms with generic phrases like everyday productivity words, making the skill eligible in far too many conversations. In an agent routing system, this increases the chance of misfires, prompt collisions, and untrusted workflow application where the user did not intend to use this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.