Security audit

Work Productivity Self Improving Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

The skill is documentation-only and not malicious, but its very broad triggers plus implicit invocation could cause it to steer many unrelated user requests.

Install only if you are comfortable with this skill being auto-selected for broad productivity, learning, bug-fix, and self-improvement phrasing. Safer publication would narrow the trigger phrases and disable or tightly constrain 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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description says to use the skill whenever a user asks for broad categories like 'work-productivity' or 'self'/'improving' and for nearly any 'workflow, artifact, checklist, analysis, or implementation support' related to the requirement. This ambiguous invocation guidance can cause the skill to activate across a wide range of benign conversations, increasing the chance of prompt collisions, inappropriate tool selection, and unintended influence over agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords include extremely generic terms like 'self', 'improving', and 'proactive', which can match ordinary user requests unrelated to this skill. That creates over-broad activation and skill routing risk, causing the agent to invoke this skill in unintended contexts and potentially override more appropriate safety or domain-specific behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: 触发关键词包含非常宽泛的通用词，如“self”“improving”“proactive”“learning”等，容易在大量无关上下文中误触发该技能。误触发会让代理在并不需要该技能时加载其工作流，导致行为偏离用户真实意图、上下文污染，且在多技能环境中会放大路由错误。
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 overly broad and include common phrases such as 'Help me' and 'I need a practical workflow,' which can cause the skill to activate in contexts far beyond its intended scope. In an agent environment, this increases the risk of unintended routing, prompt capture, or execution of a workflow the user did not explicitly request, especially because the skill is framed as proactive and self-improving.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad and generic, using common terms like "self," "improving," and "proactive," which can cause the skill to activate in unrelated contexts. In an agent ecosystem, ambiguous activation can misroute user requests, override more appropriate skills, or unintentionally inject this workflow into tasks where it was not intended, reducing reliability and potentially affecting downstream safety-sensitive behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad, natural-language sentences that can easily overlap with ordinary user requests, increasing the chance this skill activates unintentionally. Because the skill is positioned as a proactive/self-improving workflow helper, accidental invocation could steer unrelated conversations, alter agent behavior, or cause the agent to produce workflow artifacts the user did not explicitly request.
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 broad restatements of the requirement and do not demonstrate precise boundaries for activation. In practice, examples like these train matching systems or maintainers toward permissive invocation, which can increase accidental activation frequency and reduce predictability.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: 技能描述中的启用条件覆盖面过大，几乎任何与 productivity、self、improving、proactive 相关的请求都可能被解释为适用场景，但没有明确列出不适用边界。这会造成技能路由过宽，使代理可能优先采用不恰当的流程、模板或自动化建议，降低系统可预测性与安全性。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 示例触发句只展示了正向触发案例，且表述高度重复、边界模糊，没有说明哪些相似请求不应调用该技能。这会使实现者或路由器难以校准触发范围，增加误调用和与其他技能冲突的概率。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The default prompt is highly generic and includes broad terms like work productivity, self-improving, proactive, workflow, checklist, and analysis, which can match common user requests unrelated to this specific skill. In combination with agent routing, this raises the chance of unintended activation, causing the skill to inject behavior or guidance into conversations where the user did not explicitly request it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without a narrowly scoped trigger surface allows the skill to be auto-selected based on vague conversational overlap rather than explicit user choice. Because this skill is framed broadly around productivity and self-improvement workflows, unintended invocation could alter responses, create confusing agent behavior, or expand the skill's influence across many benign requests.
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 Chinese-language README variant, but it does not state that language selection is optional or that the skill supports multiple locales. Because the document presents the user-facing description entirely in Chinese without an opt-in note, it may imply a locale-specific experience without documented choice or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The usage section presents trigger sentences only in English and does not indicate that users may invoke the skill in another language. Because the document references Chinese-language sources and audiences, this can be read as implicitly forcing one language without an explicit opt-in or documented locale limitation.
Content: No source excerpt is available for this finding.