Finance Autopilot
v1.0.0A proactive personal finance manager for AI agents. Tracks income and expenses, monitors subscriptions and bills, detects unusual spending, builds monthly bu...
⭐ 0· 250·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The skill's name and description match the runtime instructions: it explains expense tracking, budgeting, subscription audits, alerts, and savings suggestions. It does not request cloud/bank credentials or system-level access. A small note: some claimed capabilities (automatic detection of renewals, exact billing amounts, tax deadlines) typically require access to billing emails or bank feeds — the SKILL.md instead relies on users forwarding receipts/invoices, which is a proportionate way to achieve those features without extra credentials.
Instruction Scope
The instructions stay within the domain of personal finance: parse amounts/merchants/dates from user-forwarded receipts, categorize expenses, run periodic reports, and surface alerts. They do not instruct the agent to read unrelated files, environment variables, or external endpoints. However, the skill specifies automatic triggers (e.g., monthly reports, weekly reminders, automatic alerts after each logged expense). Those autonomous behaviors will process sensitive financial data whenever invoked, so users should understand how and when the agent will run these tasks.
Install Mechanism
There is no install spec and no code files: this is an instruction-only skill. That minimizes on-disk installation risk and means no external binaries or downloads are introduced by the skill itself.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. This is proportionate to the described approach (user-forwarded receipts rather than automatic bank or email integration). If you later ask the agent to integrate with calendars, email, or bank accounts, additional permissions would be required but are not requested by this skill.
Persistence & Privilege
always is false (not force-included). Model invocation is allowed (default), meaning the agent can autonomously run the reported automatic triggers (monthly reports, weekly reminders, immediate alerts). Autonomous invocation is expected for this kind of skill but increases the privacy/availability of processed financial data — confirm and control the agent's autonomy settings if you want stricter manual control.
Assessment
This skill appears coherent and does not request credentials or install code, but it will process highly sensitive financial data you forward to it. Before installing or using it: 1) Confirm how the agent stores and retains the parsed data and how to delete it; 2) Only forward receipts/invoices you are comfortable having processed and avoid forwarding full bank statements if you don't want account numbers shared; 3) If you want calendar or email integration (automatic ingestion), require explicit additional permissions and ask for details about where credentials are stored; 4) Consider restricting autonomous runs (so reports/alerts require your confirmation) while you test the skill with synthetic or redacted data; 5) Ask the skill author or provider for a privacy/data-retention policy if you plan to use it for real financial records.Like a lobster shell, security has layers — review code before you run it.
billsvk97eb4585zqh38hwnraxxqp4j582eqebbudgetvk97eb4585zqh38hwnraxxqp4j582eqebfinancevk97eb4585zqh38hwnraxxqp4j582eqeblatestvk97eb4585zqh38hwnraxxqp4j582eqebmoneyvk97eb4585zqh38hwnraxxqp4j582eqebsubscriptionsvk97eb4585zqh38hwnraxxqp4j582eqeb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.