ClawHub
Back to skill

Security audit

Work Productivity Proactive Agent Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

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

Installers should be aware that this skill may be invoked too broadly because of generic keywords and implicit invocation. It is best suited for explicit requests about proactive-agent workflow design, reliability, hardening, or adjacent skill planning.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (11)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use the skill when a user asks for broad concepts like "work-productivity," "proactive," "transform," "task," or any practical workflow/artifact/checklist/analysis support. This ambiguous scope can cause the system to route many unrelated requests into this skill, leading to incorrect behavior, prompt collisions with more specialized skills, and reduced reliability of agent decision-making.

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 very generic terms such as "proactive," "task," "needs," and "bug fix," which can match a wide range of ordinary user requests unrelated to this skill. Overly broad activation criteria increase the chance of unintended invocation, causing the agent to apply the wrong workflow, leak contextual assumptions into unrelated tasks, or interfere with safer/more appropriate skills.

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“transform”“task”“needs”“followers”“partners”等过于常见、语义宽泛的日常词汇，容易在与该技能无关的普通对话中被误触发。误触发会让代理进入与用户真实意图不匹配的工作流，导致错误建议、上下文污染，或在自动化环境中触发不必要的后续动作。

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 enough to activate on generic terms like 'task', 'proactive', or 'bug fix', which can cause the skill to run outside the user's intended context. In an agent setting, over-broad activation increases the chance of unintended workflow injection, confusion, or automatic execution of a mismatched skill that produces unsafe or irrelevant actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrases are broad and generic, including common terms like 'task', 'transform', and 'proactive', which can cause the skill to activate in many unrelated contexts. In an agentic workflow, over-triggering can route user requests into unintended behavior, increasing the chance of prompt interference, mis-execution, or accidental use of this skill when a more appropriate and safer skill should handle the request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

该文件仅提供 zh-CN 内容，且未说明是否可根据用户语言偏好切换，可能导致默认以特定语言输出或在多语言环境中被错误选用。这通常不是直接安全漏洞，但会增加误解、错误执行步骤和用户确认不足的风险，尤其在涉及配置、修复或安全加固说明时更容易产生操作偏差。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

技能描述中的适用范围覆盖“work-productivity, proactive-agent, proactive, transform, task”以及“需要实用流程、产物、检查清单、分析或实现支持”等宽泛场景，边界非常模糊。这样的激活条件会扩大匹配面，使路由器或调用方难以准确区分何时应启用该技能，从而增加误调用、错误委派和结果偏离用户需求的风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest’s invocation text is excessively broad and ambiguous, using generic terms like work-productivity, proactive, transform, task, checklist, analysis, and implementation support. Combined with allow_implicit_invocation: true, this increases the chance the skill will be auto-invoked in situations the user did not intend, which can cause prompt-scope confusion, unnecessary exposure of user context to the skill, or unsafe workflow steering.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger sentences are so broad and fragmentary that they can match ordinary user requests unrelated to this skill’s intended scope, causing accidental invocation or routing confusion. In an agent ecosystem, this can lead to over-application of the skill, unexpected behavior, and reduced trust in automation, especially when keywords like 'help me', 'practical workflow', 'task', or 'needs' are common across many benign prompts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The README states that the skill includes English and Chinese instruction and guide files, but it does not explain how the user's preferred language is selected. That can create an implicit locale policy issue if the skill defaults to a language without user opt-in or clear documented behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This Chinese README presents key operational text, including the workflow description and trigger phrases, in English without stating that English is required or optional. That can impose a language preference on users without opt-in, which is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.