Security audit

Work Productivity Proactive Agent Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no harmful runtime behavior found, though its activation wording is broader than ideal.

Installers should know this skill may be selected for overly broad productivity or task-related prompts. It is best used when explicitly working on proactive-agent workflow design, reliability hardening, bug-fix workflows, or adjacent skill creation; maintainers should narrow the trigger phrases before relying on implicit invocation.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description says to use the skill when a user asks for broad concepts like "work-productivity," "proactive," "transform," or "task," which provides ambiguous activation guidance and materially expands the matching surface. In a skill-selection system, such language can cause unintentional invocation on benign, unrelated prompts, reducing routing integrity and potentially exposing users to incorrect workflows or outputs.
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 generic terms like "proactive," "transform," "task," "needs," and "bug fix," which are common in normal user requests and can cause accidental skill activation. Overbroad activation increases the chance this skill intercepts unrelated conversations, leading to prompt-routing errors, unintended instruction injection into downstream workflows, or suppression of more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The top-level description says the skill should be used whenever users ask for broad categories like work-productivity, proactive, transform, or task, which creates unclear boundaries for activation. This makes accidental invocation likely and increases the chance that unrelated user requests are handled by this skill, reducing reliability and potentially bypassing more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords include very broad everyday terms such as "task", "needs", and related generic words, which can cause the skill to activate in many unrelated contexts. In an agent environment, over-broad activation can route user requests into the wrong workflow, causing unintended actions, irrelevant guidance, or unsafe application of this skill to contexts it was not designed for.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentences are extremely broad and include common words like "help me," "practical workflow," and generic task-oriented phrasing, which can cause the skill to activate for many unrelated user requests. In an agent-routing context, overbroad activation can misroute conversations, override more appropriate skills, and lead to unintended processing of user input under the wrong workflow assumptions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger keywords include very generic terms such as "task," "transform," and "needs," which can cause the skill to activate for ordinary user requests far outside its intended scope. In an agent ecosystem, over-broad activation increases the chance of unintended instruction injection, workflow hijacking, or accidental handling of requests by an ill-suited skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The example trigger sentences are vague and begin with broad phrases like "Help me" and "I need a practical workflow," which are common across many unrelated user intents. This makes accidental or excessive routing more likely, weakening skill-selection boundaries and potentially causing the agent to apply this workflow in inappropriate contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords and example activation phrases are very broad, including generic terms like 'task', 'transform', 'needs', and 'bug fix'. In an agent ecosystem, this can cause the skill to activate in contexts far beyond its intended scope, increasing the chance of unintended workflow execution, prompt hijacking through ambiguous routing, or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger phrases are themselves broad and truncated, and they do not show any negative examples or boundary conditions. This trains invocation logic and maintainers toward permissive matching, reinforcing accidental triggering and making the skill’s scope harder to control.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description and default prompt are overly broad, using generic triggers like work-productivity, proactive-agent, transform, task, checklist, analysis, and implementation support. Combined with allow_implicit_invocation: true, this increases the chance the skill is auto-invoked in contexts the user did not clearly intend, which can cause unintended actions, prompt hijacking exposure, or confusing tool selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This file is a zh-CN README, but the core usage text and trigger phrases are written in English only. That effectively forces a specific language for activation or operation without stating that users can choose their preferred language or that English is required for a justified reason.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The file includes mixed English and Chinese content in evidence links and titles, but does not state whether the skill will preserve source language, translate content, or ask the user for a preferred language. That can create an implicit language/locale behavior without user choice.
Content: No source excerpt is available for this finding.