Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only helper with broad trigger wording, but no hidden code, credential access, persistence, or destructive behavior was found.
This skill is reasonable to install if you want a general AdMapix-style workflow helper. Review or narrow its trigger keywords before relying on implicit invocation, because generic words like data, raw, and layer may cause it to activate for unrelated software tasks.
The trigger sentence begins with a broad, natural-language phrase ('Help me ...') that is common in ordinary user requests and not narrowly tied to this skill’s specific scope. In an agent routing system, this can cause unintended invocation of the skill on unrelated prompts, exposing the system to misrouting, over-broad tool use, or accidental processing of data outside the intended workflow.
The trigger phrase starts with generic everyday language such as 'Help me' and 'I need', which can cause the skill to activate on ordinary user requests that were not intended to invoke it. In an agent ecosystem, overly broad activation increases the chance of prompt-routing collisions, unintended execution, and accidental exposure of this skill's instructions in unrelated contexts.
The trigger phrases are extremely broad and include generic language like 'Help me' and 'I need a practical workflow', which can cause the skill to activate for unrelated user requests. In an agent environment, overbroad invocation increases the chance of unintended routing, context confusion, and accidental execution of workflows on inputs the user did not mean to handle with this skill.
The manifest description says to use the skill when a user asks for broad categories like 'software-and-data' or needs almost any 'workflow, artifact, checklist, analysis, or implementation support,' which is far too expansive. This creates a routing vulnerability where ordinary technical requests may incorrectly invoke the skill, reducing predictability and potentially bypassing more appropriate, specialized skills.
The trigger keywords are overly generic terms such as 'raw', 'data', 'layer', and 'bug fix', which can match many unrelated user requests and cause unintended skill activation. Over-broad activation increases the chance that this skill will intercept prompts outside its intended scope, leading to confused routing, irrelevant guidance, or unsafe reliance on a mismatched workflow.
技能描述中的触发条件覆盖了多个宽泛主题词，并将“需要流程、产物、检查清单、分析或实现支持”这类常见求助意图直接作为使用条件，容易在与该技能并不强相关的普通软件/数据请求中被误触发。这会导致错误路由、输出与用户真实目标不匹配，且在安全场景下可能绕过更合适的专用技能或审查流程。
关键词列表包含"raw"、"data"、"layer"、"apps"等高频泛化词，缺少组合条件、上下文限定和排除条件，极易匹配到大量无关请求。若攻击者或普通用户仅使用这些常见词，就可能诱导系统调用该技能，造成越权式能力暴露、错误建议注入或对本应由其他更安全技能处理的任务进行接管。
The default prompt uses a very broad activation phrase tied to generic terms like software, data, and workflow support, which can cause the skill to be invoked in contexts far beyond its intended scope. Because implicit invocation is enabled, this increases the chance of unintended triggering, prompt-scope confusion, and accidental exposure of the skill’s instructions or behavior in unrelated user requests.
This trigger is ambiguous and incomplete, describing a generic need for a 'practical workflow' without clear boundaries for the subject matter or required inputs. Because the skill is for software/data implementation support, ambiguous activation increases the chance that unrelated developer, data, or safety requests will invoke it, leading to unreliable routing and potentially unsafe downstream actions if the skill produces implementation guidance in the wrong context.
This file is a Chinese-language README, and the usage guidance and trigger descriptions are presented only in Chinese without any opt-in or note about language selection in this document. That may conflict with a language-choice policy if users are not explicitly offered a locale option here.
The example trigger sentences are vague and self-referential, reinforcing activation on imprecise phrases instead of demonstrating narrow, realistic use cases. This makes accidental invocation more likely because downstream systems or authors may treat these weak examples as acceptable matching patterns.
示例触发句采用了"Help me"、"I need a practical workflow"这类日常表达，只在后半句附带模糊需求描述，容易与普通技术求助语句重叠。虽然其危险性低于直接的不安全指令，但它会放大前述宽泛关键词问题，使路由器或调用方更难区分何时应真正使用该技能。
