Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-help skill for OpenAPI and Swagger work, with some sloppy broad trigger wording but no artifact-backed harmful behavior.
Reasonable to install if you want help with OpenAPI or Swagger documentation. Be aware it may activate on broad API documentation wording, so invoke a more specific skill manually if you need unrelated backend help.
The trigger phrases are generic and malformed enough that the skill could activate on loosely related user requests, causing unintended routing or invocation. In an agent system, overly broad activation increases the chance of context confusion, inappropriate tool selection, and accidental exposure of internal skill behavior when a narrower skill should have handled the request.
The trigger phrases are broad and loosely scoped, so the skill may activate for generic software, API, or documentation requests that were not intended to invoke this specific workflow. In an agent system, overbroad activation can cause inappropriate tool/skill selection, unnecessary exposure of user context to the skill, and increased attack surface for prompt-routing manipulation.
The manifest description says to use the skill when a user 'needs a practical workflow, artifact, checklist, analysis, or implementation support,' which is a very broad activation condition that overlaps with many ordinary engineering requests. It does not clearly constrain when the skill should activate beyond a loose topic list, increasing the risk of unintended invocation.
The example triggers use broad phrases like 'Help me' and 'I need a practical workflow,' which are common everyday requests and not specific enough to this skill. The examples also appear truncated and do not provide clear positive or negative boundaries for activation.
The skill description uses a broad set of user intents and keywords to determine applicability, which increases the chance of accidental invocation outside the intended OpenAPI/Swagger documentation use case. Overbroad routing can cause the wrong skill to handle unrelated prompts, producing misleading guidance or causing prompt-scope confusion across the agent.
The trigger keyword list includes broad phrases such as 'software-and-data' and general API-related terminology that can match many ordinary requests. This makes unintentional activation more likely, which can misroute conversations and expand the skill's operational scope beyond what the author likely intended.
The example trigger phrases are written as generic help-seeking sentences, which are likely to overlap with normal user language. If the router relies on these patterns, the skill may be selected for routine requests that only loosely resemble the intended domain, reducing reliability and potentially interfering with more appropriate skills.
The skill enables implicit invocation, but the trigger scope is only broadly described through metadata and not constrained by explicit conditions. This can cause the agent to invoke the skill in unintended contexts, increasing the chance of prompt-scope expansion, accidental data exposure to the skill, or user confusion about when specialized behavior is being applied.
The trigger phrases are so broad and awkwardly templated that they can match ordinary user language or partial requests unrelated to explicit invocation of this skill. That increases the chance of accidental activation, causing the agent to apply this skill in the wrong context and potentially override more appropriate routing or expose internal workflow behavior unexpectedly.
The natural-language description lists English and Chinese instruction and guide files, but does not state how the user's preferred language is selected or whether language choice is optional. This can create a locale-policy concern if the skill defaults users into a language without explicit opt-in.
