Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-helper skill for OpenAPI/Swagger work, with some overly broad trigger wording but no hidden execution, persistence, or sensitive access.
Installers should be aware that the skill may activate for broad API or developer-experience wording; prefer explicit use for OpenAPI or Swagger documentation tasks.
The trigger phrases are so generic and repetitive that the skill may activate for loosely related requests, causing unintended routing or execution in contexts the user did not clearly choose. In an agent ecosystem, ambiguous activation increases the risk of prompt confusion, inappropriate tool use, and reduced user control, even though this README does not itself contain code execution logic.
The trigger phrases are generic and malformed enough that they could cause the skill to activate in situations broader than intended, especially for common API- and documentation-related requests. Over-broad activation can route user prompts into the wrong workflow, causing unintended handling of inputs, confusion, or inappropriate disclosure of internal guidance in multi-skill environments.
The skill description and activation guidance are broad enough that the skill may trigger in routine discussions about APIs, documentation, or developer experience rather than only when the user explicitly wants OpenAPI-documentation help. Over-broad activation increases the chance of incorrect routing, unintended context capture, or the skill steering conversations it was not meant to handle.
The keyword triggers include generic phrases like 'software-and-data', 'api documentation', 'rest api', and 'developer experience', which are common across many unrelated technical conversations. This creates a realistic risk of trigger collision, causing the wrong skill to activate and potentially bias outputs or expose irrelevant instructions in contexts outside OpenAPI documentation work.
The trigger description is broad enough to overlap with many ordinary technical discussions about APIs, software, or documentation. This can cause unintended activation of the skill, routing user requests into a narrower workflow than intended and potentially producing irrelevant or lower-quality outputs.
The keyword list includes highly generic terms such as software-and-data, openapi, swagger, and developer experience without scope guards or exclusion rules. In a skill-routing system, this increases the chance of accidental invocation during unrelated conversations, which can misdirect agent behavior and degrade task selection reliability.
The skill enables implicit invocation while using a broad default prompt and description tied to common OpenAPI/Swagger help requests. This can cause the agent to activate the skill without clear user intent, potentially exposing unreviewed guidance or causing unintended workflow changes in unrelated conversations where API documentation is only mentioned incidentally.
The trigger sentence begins with an everyday phrase ('Help me') and then appends a long requirement description, making activation criteria overly broad and likely to match unrelated user requests. In an agent-routing context, this can cause unintended invocation of the skill, leading to confused delegation, disclosure of irrelevant context, or unsafe overreach into tasks the user did not intend this skill to handle.
The trigger sentence is ambiguous because it says 'I need a practical workflow for ...' followed by a truncated, generic requirement statement rather than a concrete user intent. Ambiguous triggers increase the chance that the orchestration layer selects this skill for loosely related requests, which can misroute conversations and degrade safety by applying the wrong capability to user input.
The file lists separate English and Chinese instruction and guide files, but does not state how the user's preferred language is selected or that language choice is user-driven. This can create a locale-policy concern if the skill defaults to a language without explicit opt-in.
In a zh-CN README, key user-facing behavior descriptions and all trigger phrases are written in English, which can implicitly require English usage despite the localized filename. The file does not state that users may interact in Chinese or choose their preferred language.
The example trigger sentences are malformed, truncated, and do not provide clear safe invocation patterns. Poor examples can lead to unreliable or accidental activation behavior, making routing less predictable and increasing the chance that users or upstream systems invoke the skill in unintended situations.
The file embeds Chinese-language evidence titles and references but does not clarify language expectations or offer a language/locale choice for users. This can create a language-policy concern if the skill implicitly surfaces or relies on a specific language without user opt-in.
No suspicious patterns detected.
