Skillv0.1.0

ClawScan security

Financial Planning · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignFeb 13, 2026, 8:53 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only financial planning playbook whose requested resources and runtime instructions align with its stated purpose — it does not request credentials, install software, or perform unexpected actions.
Guidance: This skill is a text-based playbook for financial planning and appears internally consistent. Before installing: consider that the skill's author/source is unknown (there's no homepage or owner details), so only share non-sensitive, aggregated financial numbers (avoid pasting bank account numbers, full transaction histories, authentication tokens, or other secrets). Treat its advice as a helpful template, not professional accounting or tax advice. If you plan to let an autonomous agent use this skill, ensure you’re comfortable with it accessing any financial figures you provide during interactions.

Purpose & Capability: okThe name and description (budgeting, cash flow, P&L) match the SKILL.md content. All required inputs are user-provided financial figures; there are no unrelated requirements such as cloud credentials or system access.
Instruction Scope: okThe SKILL.md gives step-by-step guidance for collecting financial numbers, building budgets, and running monthly reviews. It does not instruct the agent to read local files, access environment variables, call external endpoints, or exfiltrate data. (The file is truncated in the manifest but the visible content remains scoped to financial planning.)
Install Mechanism: okNo install spec and no code files are present. Because this is instruction-only, nothing will be written to disk or downloaded during install.
Credentials: okThe skill declares no environment variables, no credentials, and no config paths — which is proportional for a guidance/playbook style skill.
Persistence & Privilege: okalways is false and the skill does not request persistent system privileges. The default ability for the agent to invoke the skill autonomously is normal and not a concern here given the skill's non-sensitive scope.