Security audit
Security checks for vulnerabilities and agentic risk
This is a simple OpenAPI/Swagger documentation helper with broad activation wording but no hidden code, persistence, credential handling, or destructive behavior.
Install this if you want help with OpenAPI or Swagger documentation. Be aware that its broad keywords may cause it to activate for some general API or developer-experience conversations, so review whether it is the right skill for the task before accepting generated changes.
The trigger sentences are vague and expansive enough that the skill could activate on loosely related requests, causing it to handle tasks outside its intended OpenAPI documentation scope. In an agent environment, overbroad routing can expose users to incorrect automation, unintended prompt injection surface, or misapplication of the skill to sensitive backend/API contexts.
The trigger phrases are generic and match broad user intents like asking for help or a practical workflow, which increases the chance this skill activates when the user did not explicitly request this specific capability. In an agent system, unintended activation can route requests into the wrong workflow, causing prompt-scope confusion, disclosure of unrelated context, or execution of actions under an inapplicable skill.
The skill description is broad enough that it may match many general requests involving APIs, software, or documentation, causing the skill to activate outside its intended niche. Over-broad invocation can route users into an irrelevant workflow, increasing the chance of bad guidance, unintended file access, or misuse of downstream tooling in contexts the skill was not designed to handle.
The trigger keywords include ambiguous phrases like 'software-and-data' and 'developer experience' that are far broader than the actual scope of an OpenAPI documentation skill. This can lead to unintended invocation on unrelated prompts, making the agent apply this skill in unsafe or low-relevance situations and potentially exposing users to incorrect automation paths.
The skill description says to use the skill for broad topics like software-and-data, OpenAPI, Swagger, API documentation, and REST API, without enough boundary conditions. This can cause the skill to activate in unrelated conversations about APIs and documentation, increasing the chance of inappropriate routing, over-collection of context, or unintended assistance outside its intended scope.
The keyword list includes broad terms such as openapi, swagger, api documentation, and developer experience, which frequently appear in normal engineering discussions. Such generic triggers can cause accidental invocation of the skill in contexts that do not require documentation generation, leading to misrouting and potentially unsafe or irrelevant automated guidance.
The default prompt uses broad, natural language phrasing covering general backend, platform, software-and-data, API documentation, workflows, artifacts, checklists, and implementation support. This overlap with common developer requests makes accidental invocation more likely, which can lead to overbroad skill activation and unintended exposure of user context to the skill.
The skill enables implicit invocation without any narrowly scoped activation guard, which can cause the agent to auto-select this skill for loosely related requests. Because the skill description and prompt target broad API/documentation help, this increases the chance of unintended routing, context leakage into the skill, or the skill influencing conversations where the user did not explicitly request it.
The trigger sentence is extremely broad and can activate on ordinary user phrasing rather than a clear, constrained invocation. This creates scope-confusion risk: the skill may be selected in unintended contexts, causing it to override more appropriate skills or process unrelated prompts under an OpenAPI-documentation workflow.
The activation phrase is ambiguous because it does not define concrete prerequisites, inputs, or domain-specific constraints beyond generic request language. An ambiguous trigger increases the chance of accidental routing, which can lead to inappropriate skill execution, prompt hijacking of normal conversation flow, or reduced reliability of downstream safety and task selection.
The file lists English and Chinese variants for instructions and guides, which may imply a fixed language/locale offering. Because no user choice, opt-in, or justification for limiting locales appears here, this can be read as a language/locale policy concern.
The example trigger phrases are malformed and truncated, so they do not provide reliable boundaries for when the skill should run. Poor examples make trigger behavior harder to audit and can normalize overly permissive matching, which increases accidental activation risk.
No suspicious patterns detected.
