Security audit
Security checks for vulnerabilities and agentic risk
The skill is a non-executable budgeting helper, but its automatic activation is too broad for a workflow that may involve sensitive bank and card transaction data.
Review this skill before installing if you use automatic skill invocation. It appears safe as a manual budgeting helper, but its triggers should ideally be narrowed to explicit bank export, CSV/OFX import, transaction categorization, subscription audit, or cash-flow cleanup requests before using it around private financial data.
The trigger sentence is overly broad and can cause the skill to activate on common budgeting or finance requests that may not actually require this specific workflow. Overbroad activation increases the chance of inappropriate routing, which can override more suitable skills or inject irrelevant guidance into unrelated financial tasks.
The trigger sentence starts with a common phrase ('Help me') and then embeds a broad requirement description, which makes accidental invocation more likely during normal user conversation. In an agent ecosystem, overly generic activation text can cause this skill to run outside its intended budget/cash-flow context, potentially exposing user financial data to the wrong workflow or causing confusing, unintended task routing.
The trigger pattern 'I need a practical workflow for ...' is broadly worded and could match many benign requests that are only loosely related to budgeting. Because this skill deals with potentially sensitive financial workflows, loose activation increases the chance of unintended engagement and misrouting of transaction or cash-flow tasks.
The trigger phrases are broad enough to match many ordinary finance-related requests, which can cause the skill to activate when the user did not explicitly intend it. In an agent ecosystem, this increases the risk of inappropriate routing, prompt-context hijacking, or the skill taking over tasks outside its narrow scope, especially because the phrases include common terms like budget, cash flow, and workflow.
The skill description contains broad activation terms such as business-and-operations, budget, cash flow, bank export, transaction categorization, and implementation support, which can match many ordinary user requests beyond the narrow intended use case. Over-broad routing can cause this skill to activate in unrelated contexts and expose users to inappropriate workflows, mistaken data handling guidance, or unintended collection/use of sensitive financial information.
The trigger examples are phrased as common everyday requests and directly encourage invocation of the skill for broad, natural-language prompts without meaningful constraints. This increases the chance of accidental or excessive activation, especially in mixed financial conversations where the user did not intend transaction-cleanup support, potentially leading to mis-scoped advice around sensitive personal or business finance data.
The trigger keywords are broad business terms such as 'budget' and 'cash flow', which can match many ordinary conversations outside the intended skill scope. This can cause over-triggering, leading the agent to invoke the skill in unrelated contexts and potentially expose users to irrelevant financial guidance or unintended handling of sensitive transaction-related requests.
The example trigger sentences are highly generic and mirror broad user intents without clear qualification, which reinforces permissive matching behavior. In practice, this increases accidental activation risk and may route vague business questions into a workflow intended for transaction cleanup and budgeting artifacts.
The skill enables implicit invocation while its trigger description is extremely broad, covering generic business, budgeting, cash-flow, analysis, workflow, and implementation support requests. This can cause the agent to auto-activate in situations the user did not clearly intend, increasing the chance of unnecessary access to sensitive financial context and unintended reliance on this skill's guidance.
The activation examples are ambiguous, truncated, and lack clear boundaries for when the skill should or should not run. In a routing system, this can lead to accidental invocation on ordinary business or budgeting requests, creating prompt-scope confusion and reducing the reliability of skill selection.
Although this is a Chinese README, substantial user-facing content such as the title, demand description, workflow description, keywords, and trigger phrases remains in English. This can effectively impose a language choice on users without opt-in or explanation, which is a natural-language locale policy concern under the stated rule.
No suspicious patterns detected.
