Security audit
Security checks for vulnerabilities and agentic risk
This is a simple OpenAPI/Swagger documentation helper with some overly broad trigger wording but no hidden code, persistence, credential handling, or destructive behavior.
This skill is reasonable to install for OpenAPI or Swagger documentation work. Be aware that its trigger wording is broad and may cause accidental activation for general API or developer-experience questions; prefer explicit invocation when you want it, and ignore or disable implicit activation if precise routing matters.
The trigger sentence begins with an everyday phrase ('Help me') and then appends a long requirement description, making activation scope overly broad and easy to match unintentionally. In an agent-routing context, ambiguous triggers can cause the skill to activate for unrelated user requests, leading to misrouting, unexpected behavior, or unnecessary exposure of downstream tooling and instructions.
The trigger phrases are generic and malformed enough that they could match loosely related user requests and cause the skill to activate unexpectedly. In an agent environment, unintended invocation can route a conversation into the wrong workflow, leading to irrelevant guidance, prompt-surface expansion, or downstream actions based on misunderstood intent.
The trigger phrases are broad and generic enough that the skill could activate for loosely related requests about software, APIs, or documentation rather than explicit OpenAPI documentation tasks. In an agent system, ambiguous activation can cause the wrong skill to take control, leading to unintended instruction injection into the workflow, incorrect outputs, or bypass of more appropriate safeguards tied to narrower skills.
The skill description and activation criteria are broad enough to match many generic software or API-related requests, which can cause the skill to trigger outside its intended scope. Over-broad activation increases the chance of inappropriate routing, irrelevant instructions, or accidental application of this skill in contexts where more specialized or safer handling is needed.
The keyword triggers include generic terms such as 'openapi', 'swagger', and especially 'developer experience', which may appear in many unrelated conversations and cause unreliable activation. This can result in the skill being invoked for requests that do not actually seek documentation-generation support, degrading routing integrity and potentially surfacing unsuitable guidance.
The trigger keywords include broad, commonly used terms such as 'software-and-data', 'openapi', 'swagger', 'api documentation', and 'rest api', which can overlap with many ordinary developer-assistance requests. This increases the chance the skill activates when not specifically intended, causing prompt-context hijacking of unrelated conversations and potentially steering users into this skill's workflow without clear consent.
The example trigger phrases begin with generic help-seeking language like 'Help me' and 'I need a practical workflow', which closely resembles normal user requests. In systems that learn or match from examples, this can cause over-triggering on routine assistance prompts, routing unrelated tasks into this skill and increasing the attack surface for unintended prompt injection or mis-scoped automation.
The skill enables implicit invocation but does not define narrow trigger constraints or other guardrails in this file. That increases the chance the agent will auto-select this skill in loosely related conversations, causing unreviewed prompt/context flow into the skill and potentially broadening attack surface through unintended activation.
The sentence 'I need a practical workflow for ...' is generic and does not clearly constrain when the skill should be invoked. Ambiguous activation language increases the chance that normal project-planning or workflow questions unrelated to API documentation will trigger this skill, degrading routing integrity and potentially exposing users to irrelevant or unintended instructions.
The file mixes English-facing documentation with Chinese-language evidence links and advertises a Chinese skill variant, but does not state how language selection is determined. This can create ambiguity about locale behavior and whether users are given an explicit language choice.
The example trigger sentences are malformed and vague, which makes intended invocation patterns unclear and weakens safeguards around correct routing. Ambiguous examples can train users or calling systems to invoke the skill imprecisely, increasing accidental activation and inconsistent behavior.
The evidence section includes multiple Chinese-language titles and labels, but the document provides no indication of language preference handling or user opt-in for locale. This can create a language/locale policy concern if the skill surfaces or relies on a specific language without explicitly offering a choice.
