Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only helper skill with no executable payload, persistence, credential handling, or destructive behavior, but its automatic invocation triggers are overly broad and should be tightened.
Before installing, be aware that this skill may be invoked for broad software or data requests because implicit invocation is enabled and the keywords are generic. It is reasonable to install if you want an AdMapix/raw-data workflow helper, but the publisher should narrow activation wording to AdMapix-specific phrases.
The trigger phrases are broad, repetitive, and include common request formulations such as 'Help me' and 'I need a practical workflow,' which can cause the skill to activate for loosely related requests. In an agent environment, ambiguous activation can route user tasks to the wrong workflow, causing unintended data handling, incorrect automation, or user confusion about which skill is operating.
The skill description is broad enough to activate on common software or data-related requests that are only loosely connected to the intended AdMapix-style workflow. Overbroad routing can cause the wrong skill to engage, leading to irrelevant guidance, missed safety constraints, or accidental handling of tasks outside the skill's validated scope.
The trigger sentence begins with a very broad everyday help request pattern ('Help me ...'), which can cause the skill to activate for unrelated user prompts that merely resemble the phrasing. In an agent environment, overbroad invocation increases the chance of misrouting tasks, accidental execution of the wrong workflow, and unsafe handling of requests outside the intended AdMapix/software-data scope.
The trigger sentences are broad, awkwardly truncated, and likely to match loosely related user requests, which can cause unintended activation of the skill. In an agent ecosystem, overbroad routing can expose users to the wrong workflow, produce irrelevant actions, or cause the skill to handle requests outside its intended scope, increasing the chance of unsafe or unreliable behavior.
This file presents the skill documentation entirely in Chinese, while the stated target users include broad audiences such as AI-agent users, maintainers, and teams. There is no user-facing note in this file offering language choice or explaining that the locale is intentionally limited, which can violate language/locale policy expectations.
The keyword list includes highly generic triggers such as 'raw', 'data', 'layer', 'apps', and 'bug fix', which are likely to appear in many unrelated conversations. This creates a skill-hijacking risk where the agent may invoke this skill instead of a more appropriate one, reducing reliability and potentially bypassing domain-specific safeguards.
The example trigger phrases use everyday language like 'Help me' and 'I need a practical workflow' combined with vague requirement text, which does not establish clear activation boundaries. Ambiguous examples train routers or maintainers toward over-selection, increasing the chance of accidental invocation on unrelated user requests.
The trigger keywords are overly broad and include generic terms such as 'raw', 'data', 'layer', and 'apps', which can match many unrelated user requests. This can cause accidental invocation of the skill outside its intended scope, leading to irrelevant guidance, routing confusion, or unintended exposure of workflow instructions in contexts where they do not fit.
The example trigger phrases start with highly generic formulations like 'Help me' and 'I need a practical workflow for', which are common across many benign requests and do not constrain the domain sufficiently. In a skill-routing system, these examples may reinforce ambiguous activation behavior and increase the chance of the skill being selected for unrelated tasks.
The default_prompt and description use very broad, generic language such as 'help me' and wide keyword coverage, which can overlap with ordinary user requests and cause the skill to activate outside clearly intended contexts. This increases the risk of prompt-scope hijacking, unintended routing, or silent insertion of the skill's behavior into unrelated conversations.
Enabling allow_implicit_invocation without tight trigger constraints allows the platform to invoke this skill automatically based on vague semantic similarity rather than explicit user intent. In combination with the broad manifest wording, this can cause unintended skill execution, expanded prompt influence, and unpredictable behavior in unrelated tasks.
The trigger uses a generic request template ('I need a practical workflow for ...') without strong scope boundaries, so many unrelated software or workflow questions could match. Because this skill is positioned as a helper for practical implementation support, unintended invocation could lead to irrelevant or overly trusted outputs being applied in the wrong context.
The file explicitly defines English and Chinese instruction and guide files, but does not state that users may choose their preferred language or locale. This can be a natural-language policy issue if the skill defaults to fixed languages without user opt-in.
