Work Productivity Pollyreach Gives Workflow Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:23 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with overly broad activation wording, but no hidden execution, credential use, persistence, or destructive behavior.

Before installing, be aware that this skill may activate on loosely related productivity or phone-number wording. It appears safe as a documentation workflow helper, but its triggers should ideally be narrowed to explicit PollyReach or workflow-helper 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 (11)

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The trigger phrases and keywords are broad, generic, and partially nonsensical, which increases the chance the skill will activate for unrelated user requests. In an agent ecosystem, overbroad activation can route sensitive or irrelevant tasks into the wrong workflow, causing unintended actions, confusing outputs, or unsafe delegation based on weak intent matching.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger keywords and example invocations are overly broad, including generic terms like 'every', 'phone', 'number', 'ability', and 'things', which can match many unrelated user requests. This can cause unintended activation of the skill, leading the agent to inject irrelevant workflows into normal conversations and increasing the chance of misrouting user tasks or bypassing more appropriate skills.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger keyword list includes highly generic words such as "every," "phone," "number," "ability," "things," and "done," which can cause the skill to activate for unrelated user requests. Over-broad activation can route conversations into the wrong skill, causing unintended behavior, confusion, and unsafe application of workflow guidance outside its intended scope.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The example trigger phrases are vague and mirror ordinary language rather than clear invocation cues, making accidental matching more likely. Because the examples also contain truncated, repetitive requirement text, they can encourage imprecise routing behavior and make the skill fire in contexts unrelated to PollyReach-style workflow assistance.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger keyword list includes very broad everyday terms such as "every", "phone", "number", "ability", "things", and "done", which can cause the skill to activate in many unrelated conversations. This increases the chance of unintended routing, context hijacking, or the skill being invoked when a more appropriate skill should handle the request.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill description defines activation conditions too broadly, covering a wide range of user needs like practical workflows, checklists, analysis, and implementation support around loosely related terms. This ambiguity can make the skill over-match user requests and interfere with correct skill selection or cause unintended execution paths.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger phrases reinforce permissive activation by showing generic formulations like "Help me" and "I need a practical workflow" paired with a long broad requirement statement. This trains or encourages matching behavior that can capture normal user language even when the request is not specifically about this skill's intended domain.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The default prompt includes a very broad natural-language trigger phrase tied to common productivity terms, which increases the chance of accidental invocation during ordinary user conversations. This can cause unintended routing to the skill, exposing users to unexpected behavior or tool use and making prompt-injection or misuse pathways easier to reach.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Enabling implicit invocation without tight activation constraints allows the platform to invoke the skill based on ambiguous conversational matches rather than deliberate user intent. In a broad 'workflow helper' context, this raises the risk of over-triggering, unintended execution paths, and abuse through crafted prompts that steer the agent into this skill unexpectedly.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence is so broad and generic that it can match ordinary user language unrelated to this skill, causing unintended activation. In an agent ecosystem, this can route conversations to the wrong skill, override more appropriate handling, and increase the chance that unrelated prompts are processed under assumptions or workflows the user did not request.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: Although it includes more context, the trigger still lacks precise invocation boundaries and can be matched by loosely related requests. This ambiguity increases accidental skill selection, which can degrade reliability, confuse users, and create opportunities for prompt-routing abuse if an attacker crafts text to deliberately invoke this skill.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.