Security audit

Work Productivity Self Improving Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no executable code, credentials, persistence, or hidden data access, though its activation terms are overly broad.

Installers should be aware that this skill may be selected more often than intended because its trigger words are broad and implicit invocation is enabled. Prefer explicit invocation by skill name when you want this workflow helper, and review generated plans or code changes before applying them.

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 (14)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases include extremely generic terms such as 'self', 'improving', and 'proactive', which are common in ordinary conversation and can cause the skill to activate unintentionally. In an agent ecosystem, this broad matching can hijack unrelated user requests, leading to incorrect workflow injection, confused delegation, or accidental execution of this skill instead of a more appropriate one.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says to use the skill whenever a user asks for broad concepts like work-productivity, self, improving, or proactive, without defining clear limits. Such ambiguous activation conditions can make the skill over-match benign conversation and capture requests it was not designed to handle, reducing predictability and creating opportunities for prompt-routing mistakes.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger list includes extremely generic terms like "self," "improving," and "proactive," which are common in ordinary user requests and can cause the skill to activate far outside its intended scope. This increases the chance of unintended routing, context hijacking, or interference with more appropriate skills, especially in multi-skill environments where activation terms should be narrowly scoped.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: 触发关键词包含“self”“improving”“proactive”等非常宽泛的日常词汇，容易在与该技能无关的正常对话中被意外激活。这会导致代理在错误上下文中调用该技能，造成行为偏离、提示污染或不必要地暴露该技能的工作流能力。
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt contains broad, everyday trigger terms such as 'help me' and generic productivity language that can match many unrelated user requests. In combination with a self-improving/proactive workflow skill, this raises the chance of accidental invocation, causing the agent to apply the skill outside its intended scope and potentially influence behavior or outputs unexpectedly.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Enabling implicit invocation without tight activation constraints allows the platform to auto-select this skill based on vague semantic matches. Because the skill is framed around proactive, self-improving workflows, unintended activation could let it shape task execution, recommendations, or downstream actions in situations where the user did not clearly request this behavior.
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 excessively broad and resembles ordinary user language, which can cause the skill to activate in contexts far beyond its intended scope. That creates prompt-routing risk: unrelated conversations may invoke this skill unexpectedly, exposing users to irrelevant automation, confusing behavior, or unsafe follow-on actions if downstream steps assume the trigger was intentional.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list includes highly generic terms such as "self," "improving," and "proactive," which are common in benign user conversations and can produce accidental matches. In an agent routing system, such ambiguous keywords increase the chance of misfires, causing the wrong skill to run and potentially altering outputs, workflow decisions, or downstream actions without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger sentences are broad, natural-language phrases that closely mirror ordinary user requests, which can cause the skill to activate in contexts where the user did not explicitly intend to invoke it. Because this is a proactive/self-improving workflow skill, unintended activation could redirect the agent’s behavior, inject extra workflow steps, or override a more appropriate skill selection path.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The file references separate English and Chinese documentation variants, and the reviewed file is specifically the zh-CN locale version. There is no visible language-choice or opt-in guidance in this README section, which can be read as a locale-specific presentation without explicit user selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger phrases are broad paraphrases of the requirement statement rather than precise invocation patterns, so they do little to constrain when the skill should fire. In practice, this encourages loose matching behavior and may normalize activation on vague productivity-related requests that only partially resemble the intended use case.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: 技能描述将适用范围定义为用户提到 work-productivity、self、improving、proactive 等即可能使用，边界明显过宽，未说明何时不应触发。这种模糊激活条件会增加误调用概率，使代理在普通效率类或泛化自我改进讨论中错误加载本技能。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: 示例触发句几乎复述了宽泛需求表述，但没有展示边界、负例或排除条件，会强化过度匹配行为。模型或路由器若依赖这些示例，可能把很多相似但不相关的请求错误归入该技能。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The invocation guidance is ambiguous because it defines activation using generic terms like 'self', 'improving', and 'proactive' without strong scope boundaries. In skill-routing systems, this can lead to overbroad matching and unintended invocation, making the agent easier to steer into the wrong workflow and increasing the chance of prompt confusion or misuse.
Content: No source excerpt is available for this finding.