Security audit
Security checks for vulnerabilities and agentic risk
This skill is a documentation helper for OpenAPI and Swagger work, with broad auto-invocation wording but no executable code, persistence, credential access, or hidden data handling.
Installers should expect a lightweight OpenAPI/Swagger documentation workflow. The main caveat is that its implicit invocation and broad keywords may make it appear for generic API or developer-experience requests, so users should confirm it is the right skill when the task is not specifically about API documentation.
The trigger sentence is overly broad and can cause the skill to activate on generic help requests rather than explicit OpenAPI/Swagger documentation tasks. This increases the chance of unintended invocation, which can misroute user requests, override more appropriate skills, and create prompt-scope confusion in agent workflows.
The trigger phrases are generic and template-like, making it easier for unrelated user requests to match and invoke the skill unintentionally. In an agent environment, overbroad activation can route prompts into a capability the user did not explicitly request, which may cause misleading outputs, context leakage into the skill workflow, or unsafe downstream actions if the skill later performs automated processing.
The trigger phrases are broad enough that the skill may activate on loosely related requests, causing the agent to route user interactions into this workflow without clear user intent. In an agent ecosystem, over-broad invocation increases the chance of unintended handling, prompt-scope confusion, and misuse of the skill in contexts where it was not explicitly requested.
The skill description and usage guidance are broad enough to match many ordinary API- or software-related requests, which increases the chance of unintended invocation. Over-broad activation can route users into an irrelevant or less-safe workflow, causing confused task handling, prompt-scope expansion, or accidental application of this skill where another skill or default behavior would be more appropriate.
The keyword trigger list includes generic terms such as 'software-and-data' and broad API-related phrases that lack boundaries, making accidental activation more likely. In agent systems, ambiguous keyword routing can cause the wrong skill to engage, which may expose irrelevant instructions, degrade reliability, and create opportunities for prompt-routing abuse through keyword stuffing.
The skill description uses very broad trigger terms such as software-and-data, openapi, swagger, api documentation, and rest api without clear boundary conditions. This can cause the skill to activate for loosely related requests, increasing the chance of unintended delegation, context capture, or interference with more appropriate skills.
The example trigger phrases are highly generic, such as 'Help me' and 'I need a practical workflow', and only append a broad problem statement. Generic activation examples can train or bias routing toward this skill for normal conversational requests that are not specifically asking for OpenAPI documentation assistance.
The skill enables implicit invocation while using a very broad default prompt tied to common developer requests like OpenAPI, Swagger, API documentation, and implementation help. This can cause the agent to invoke the skill in situations the user did not explicitly request, expanding the skill’s reach and increasing the chance of prompt-scope confusion, unintended data exposure to the skill, or execution of skill-specific behavior in ordinary conversations.
The invocation description uses a vague generic request pattern ('I need a practical workflow for ...') that lacks clear boundaries for when this skill should be selected. In multi-skill environments, vague routing patterns can be exploited or can accidentally capture unrelated requests, leading to incorrect tool use and reduced trust in agent behavior.
This file is labeled as a Chinese README, but multiple core user-facing sections, including the title, requirement description, workflow description, and trigger phrases, are presented in English. That creates a locale-policy mismatch because the localized file does not consistently serve the expected zh-CN audience or offer an explicit language choice.
The example trigger sentences are vague and unnatural, so they do not provide reliable boundaries for when the skill should activate. Poorly specified examples can mislead maintainers or routing systems into permissive matching behavior, increasing false activations and reducing trust in skill selection.
