Security audit

Work Productivity Ontology Typed Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

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

Install this only if you want a general ontology or typed-workflow helper, and be aware it may activate on broad terms like knowledge, graph, structured, or bug fix unless the platform lets you restrict 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 trigger phrases are broad natural-language requests such as 'Help me...' and 'I need a practical workflow...', which can match ordinary user prompts that were not intended to invoke this specific skill. In an agent ecosystem, this increases the chance of accidental activation, causing the wrong workflow to run, potentially consuming context, overriding expected behavior, or producing unintended actions based on a misrouted request.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description and activation guidance are broad enough to match many ordinary requests involving productivity, knowledge, graphs, analysis, or implementation help. This can cause inappropriate skill routing, making the agent apply this skill outside its intended scope and potentially override safer or more relevant workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The keyword list includes very generic terms such as 'typed', 'knowledge', 'graph', 'structured', and 'creating', which are common across many unrelated prompts. In an agent environment, such broad triggers can cause frequent accidental invocation, misrouting user requests and increasing the chance that the wrong skill handles sensitive or safety-relevant tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Enabling implicit invocation without narrow activation constraints allows the platform to auto-select this skill for loosely related requests. Combined with the broad skill description and prompt, this can lead to frequent over-invocation, misrouting user tasks, and unsafe cross-context behavior if the skill influences sensitive workflow or decision-making tasks.
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, generic, and partially templated in a way that could cause the skill to activate for loosely related requests rather than clear user intent. In an agent ecosystem, ambiguous activation increases the chance of workflow hijacking, misrouting, or unintended execution of a skill that may shape outputs, artifacts, or actions without the user explicitly selecting it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example trigger sentences use everyday phrasing like 'Help me' and 'I need a practical workflow,' which provides weak boundaries for when the skill should activate. These examples may train or bias routing logic toward overly permissive matching, increasing accidental selection for unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: 技能描述将适用范围定义为用户提出 work-productivity、ontology、typed、knowledge、graph，或任何“实用流程、产物、检查清单、分析或实现支持”时使用，这一边界过于宽泛，几乎覆盖大量普通生产力与知识类请求。这样的模糊启用条件会扩大攻击面和误用概率，使代理在不合适的上下文中加载该技能并输出不相关或具有误导性的流程建议。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: 触发关键词包含 "typed"、"knowledge"、"graph"、"creating"、"bug fix" 等高度常见或多义词，会让该技能在大量不相关场景中被误触发。误触发后，代理可能偏离用户真实意图，错误注入该技能的工作流与约束，造成结果污染、错误自动化决策或不必要的信息处理。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The default prompt is overly broad and generic, using common terms like productivity, workflow, analysis, and implementation support that can match many ordinary user requests. This increases the chance of unintended skill invocation, causing the agent to apply this skill outside its intended scope and potentially steer responses, tools, or outputs inappropriately.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation guidance does not clearly define activation boundaries, so the system may match on vague concepts like 'practical workflow' or 'help me' that appear in many benign conversations. In an agent ecosystem, ambiguous routing is security-relevant because it can cause unintended tool or skill selection, expanding attack surface and enabling prompt-hijack or workflow-confusion chains.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence is written as a broad natural-language phrase that overlaps with ordinary user requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. Unintended invocation can route conversations into the wrong workflow, causing incorrect task handling, prompt-scope confusion, and increased exposure to any downstream risky behavior in the skill.
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-language README contains a full English paragraph for the core requirement description, which can impose an unexpected language experience on users without opt-in. No explanation is provided that the skill is English-only or bilingual by design, and no user language choice is offered.
Content: No source excerpt is available for this finding.