Work Productivity Proactive Agent Workflow Helper

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 10:31 AM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with broad auto-invocation wording, but it does not request credentials, persistence, network execution, or other privileged behavior.

Install this only if you want a general workflow helper for proactive-agent productivity tasks. Be aware that its broad keywords and implicit invocation may cause it to activate for loosely related requests, so explicit invocation or tighter local routing rules would improve predictability.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (14)

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The trigger sentences are very broad and partially generic, including common terms like "help me," "I need a practical workflow," and keywords such as "task" and "proactive." In an agent-routing context, this can cause unintended invocation of the skill for unrelated requests, which may misroute user tasks, override more appropriate skills, or cause the agent to apply workflow transformations the user did not intend.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The manifest description defines invocation in very broad terms, including common verbs and artifact types like 'practical workflow, artifact, checklist, analysis, or implementation support'. Because many ordinary requests match this language, the skill may be selected in contexts far beyond its intended domain, increasing the chance of misrouting and unsafe instruction injection into unrelated tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The trigger list is excessively broad and includes generic terms like 'task', 'needs', and 'transform' that commonly appear in unrelated user requests. This can cause the skill to activate outside its intended scope, leading to prompt-surface expansion, unexpected workflow injection, and interference with more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The trigger list includes very broad everyday terms such as "task", "needs", and "partners", which can cause the skill to activate in many unrelated conversations. Over-broad auto-invocation increases the chance that the agent applies the wrong workflow, injects irrelevant instructions into the session, or overrides a more appropriate skill, reducing reliability and potentially affecting safety-sensitive decision paths.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The trigger sentence is extremely broad and can cause the skill to activate for ordinary user phrasing unrelated to this specific workflow. Overbroad activation increases the chance of misrouting user requests, unintended invocation, and prompt-surface expansion where this skill processes contexts it was not designed to handle.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The invocation guidance does not define clear boundaries for when the skill should and should not run, so the orchestrator or user may invoke it for vague productivity requests far beyond the documented purpose. This ambiguity increases accidental activation risk and can lead to inappropriate transformations of user intent, especially for a broadly named proactive workflow helper.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The trigger phrases are broad enough to match ordinary user language such as asking for help, practical workflows, or task handling, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this creates prompt-routing confusion and may cause the wrong workflow to process unrelated requests, reducing reliability and potentially bypassing more appropriate safety or domain-specific handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The example trigger sentences model vague activation behavior instead of clarifying precise boundaries for use. This reinforces over-selection by teaching matching systems and authors that partial, generic phrasing is sufficient, which can increase accidental invocation frequency.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The skill description defines activation conditions broadly around common productivity-related requests and generic requests for workflows, artifacts, checklists, analysis, or implementation help. This unclear boundary can cause accidental routing into the skill for unrelated user intents, creating prompt-scope confusion and weakening predictable skill selection.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The skill metadata and default prompt are extremely broad and vague, covering generic productivity, workflow, checklist, analysis, and implementation help without tight boundaries. In systems that support automatic or relevance-based routing, this can cause the skill to be invoked in unintended contexts, increasing the chance of prompt-scope confusion, unauthorized influence over unrelated tasks, or unsafe action suggestions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

Enabling implicit invocation without well-defined trigger constraints allows the platform to activate this skill automatically based on loose relevance matching. Because the skill's description is already broad, this compounds the risk of over-triggering, causing the agent to inject workflow behavior or guidance into conversations where the user did not intend to use this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The invocation description is ambiguous and lacks clear scope, so the skill may be selected for a wide range of unrelated tasks whenever users mention common terms like workflow, task, or help. In an agent environment, this can lead to inappropriate delegation, reduced reliability, and accidental handling of requests outside the intended safety and competency boundaries.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 81% confidence

Finding

The README declares English and Chinese instruction and guide files, but does not state how the user's language preference is selected or that language choice is user-driven. This can create a locale-policy concern if the skill defaults to one language without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

Although this is a zh-CN README, key descriptive and usage text remains in English, which can impose a language expectation without explicitly giving users a choice or explaining the bilingual behavior. This may conflict with language/locale policy expectations for user-facing skill documentation.

Content

No source excerpt is available for this finding.