Work Productivity Pollyreach Gives Workflow Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 6:51 AM UTC
• Version: 0.20260729.110214

Overview

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

Before installing, be aware that this skill may trigger more often than intended because its keywords are broad. It should be safe as a workflow/planning helper, but users or maintainers should narrow the trigger terms to PollyReach or outreach-workflow-specific phrases to reduce accidental activation.

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: 95% confidence
• Finding: The trigger sentences are broad enough to match ordinary user requests for generic workflow help, which can cause the skill to activate outside its intended scope. In an agent environment, overbroad activation can hijack unrelated tasks, inject irrelevant instructions, and increase the chance that a user is routed into this skill without clear consent or context.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The keyword list includes very generic terms such as 'every', 'phone', 'number', 'ability', 'things', and 'done', which are common in everyday conversation and unrelated requests. This makes accidental activation likely and broadens the skill's interception surface, especially in multi-skill agent systems that rely on keyword-based routing.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger keywords and example invocations include very broad everyday terms such as "every," "phone," "number," "ability," "things," and "done," which can cause the skill to activate for unrelated user requests. In an agent routing context, unintended activation can misroute tasks, expose the skill in contexts it was not meant for, and interfere with safer or more appropriate workflows.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The skill description is so broad that it can activate on many unrelated user requests, causing the agent to invoke the wrong workflow and potentially override more appropriate skills or safeguards. In an agentic system, overbroad routing increases the chance of unintended actions, data being handled under the wrong context, and confused-deputy style behavior.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The keyword list includes vague everyday terms such as 'every,' 'phone,' 'number,' 'ability,' 'things,' and 'done,' which are likely to match ordinary conversations that have nothing to do with this skill. This creates a high risk of accidental invocation, making the skill available in contexts where its instructions may interfere with normal agent behavior or expose users to irrelevant or unsafe workflow generation.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The example trigger phrases are ambiguous and largely restate broad requirement text rather than concrete, bounded user intents, reinforcing unsafe activation patterns. Because examples often guide matching and author behavior, vague examples can normalize over-triggering and increase misrouting across unrelated requests.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes extremely generic terms such as "every", "phone", "number", "ability", "things", and "done", which can cause the skill to activate for many unrelated requests. In an agent environment, unintended activation can hijack routing, produce irrelevant or unsafe workflow guidance, and crowd out the correctly scoped skill for the user's task.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The invocation description says to use the skill when a user asks for broad concepts like work-productivity or needs almost any practical workflow, checklist, analysis, or implementation support for the requirement. This ambiguity widens the skill's authority beyond a clearly bounded use case, increasing accidental invocation and making the agent more likely to apply this skill to unrelated tasks.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill enables implicit invocation while providing only a broad, generic description of when it should be used. This can cause the agent to auto-select the skill in unintended contexts, increasing the chance of overbroad access, unsafe action chaining, or user confusion about which workflow is being applied.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger guidance includes extremely broad everyday terms like 'every', 'phone', and 'number', which can cause the skill to activate for many unrelated user requests. Overbroad activation increases the chance of unintended routing, context capture, and misuse of the skill outside its intended PollyReach-style workflow domain.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The activation section lacks clear scope boundaries and constraints, so the skill may be selected for loosely related productivity or phone-number tasks that do not match the documented requirement. This can lead to misfires, confusing behavior, and accidental application of the skill in contexts where its assumptions or workflows are inappropriate.

VirusTotal

62/62 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.