Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-assistance skill for OpenAPI/Swagger work, with no executable payload or hidden data access found, though its activation wording is broader than ideal.
This skill is reasonable to install for OpenAPI or Swagger documentation help. Users should be aware that its broad implicit-trigger wording may activate it for adjacent API conversations, so explicit invocation with $openapi-docs-generator is preferable when possible.
The trigger sentences are broad natural-language phrases such as 'Help me...' and 'I need a practical workflow...' that can easily appear in ordinary conversation. This raises the chance of unintended skill activation, causing the agent to invoke this skill when the user did not explicitly opt in, which can misroute requests or expose context to an unnecessary workflow.
The trigger phrases are broad, templated, and partly generic (for example, 'Help me' and 'I need a practical workflow'), which increases the chance that the skill is invoked in contexts the user did not explicitly intend. In an agent system, unintended invocation can route user data or workflows through the wrong skill, causing confusing behavior, over-collection of context, or unsafe downstream actions if later skill logic is more powerful.
The skill description is broad enough to match generic requests for workflows, analysis, or implementation support beyond OpenAPI documentation. This can cause inappropriate skill routing, leading the agent to apply irrelevant instructions or artifacts in contexts the skill was not designed for, which increases the chance of unsafe or low-quality outputs.
The trigger examples use very broad everyday phrasing that does not reliably constrain invocation to OpenAPI-specific tasks. Overbroad triggers increase accidental activation and prompt-routing confusion, which can expose users to incorrect guidance or cause this skill to override a more appropriate specialized skill.
L04 将技能适用条件描述为“当用户提出 software-and-data, openapi, swagger, api documentation, rest api，或需要围绕该需求获得实用流程、产物、检查清单、分析或实现支持时使用”。其中“api documentation”“rest api”及后半句范围较宽，且没有说明哪些相关请求不应触发该技能，容易与大量普通 API 讨论重叠。
L44 仅列出关键词 openapi、swagger、rest api、developer experience 等，但未说明需要哪些关键词组合、意图前提或上下文限制。像 rest api 和 developer experience 这样的词在日常技术交流中覆盖面很广，单独作为触发依据容易造成非目标场景下的调用。
The skill enables implicit invocation while using a very broad default prompt and description that can match many routine software/API documentation requests. This increases the chance the agent will auto-activate the skill in contexts the user did not explicitly intend, potentially injecting unreviewed behavior or guidance into unrelated workflows.
The trigger sentence is so broad and malformed that it can match ordinary user requests unrelated to an explicit invocation of this skill. This creates unintended activation risk, causing the agent to route conversations into this skill unexpectedly and potentially override more appropriate handling or expose the user to irrelevant generated guidance.
The activation examples are ambiguous, truncated, and grammatically malformed, which makes the intended routing boundary unclear and increases the chance of false-positive activation. In an agent ecosystem, unclear triggers are dangerous because they can hijack benign user input into the wrong skill, degrading reliability and creating opportunities for prompt-routing abuse.
The file specifies separate English and Chinese instruction and guide files, but does not state how language selection is determined or that the user can choose their preferred language. This can create a locale-handling policy concern if the skill defaults users into a language without explicit opt-in.
This file is a Chinese-language README and does not indicate that users may choose another language or that the locale restriction is intentional for a region-specific use case. Under the policy, language constraints should be optional or explicitly justified rather than implicitly imposed.
文件名和正文均体现为 zh-CN 中文版本，但文中没有说明这是可选语言版本，也没有给用户语言选择或解释该地区/语言限制的合理性。按规则，若技能强制特定语言而无用户选择或明确 justification，属于自然语言政策风险。
