Back to skill
Skillv1.0.0
ClawScan security
个人理财预算规划助手 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 22, 2026, 2:35 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only personal budgeting assistant and its requested artifacts and runtime instructions are consistent with that purpose.
- Guidance
- This skill appears coherent and low-risk because it is instruction-only and asks only for financial information needed for budgeting. Before using it, avoid pasting highly sensitive secrets (bank login credentials, account numbers, national ID, passwords). Treat the user-provided financial figures as sensitive personal data — only supply what you are comfortable sharing and prefer aggregated or rounded amounts if you want more privacy. Also consider the platform's privacy policy: conversational data may be logged or sent to the service backing the agent, so avoid sharing information you must keep confidential.
Review Dimensions
- Purpose & Capability
- okName and description match the content of SKILL.md and reference files (budgeting frameworks, expense collection, debt strategies). No unrelated credentials, binaries, or config paths are requested.
- Instruction Scope
- okRuntime instructions only ask the agent to collect user-provided financial fields and produce budget recommendations/metrics; they do not instruct reading system files, environment variables, or sending data to external endpoints.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only, which minimizes disk writes and external code execution risk.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths. The data it requests (income, expenses, debts) is appropriate for a budgeting assistant.
- Persistence & Privilege
- okSkill is not force-enabled (always: false) and does not request persistent system privileges or to modify other skills or system configuration.