Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Just Fucking Cancel

v1.2.0

Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and provides cancel URLs. CSV-based analysis with optional Plaid integration for ClawdBot users.

2· 2.6k·4 current·5 all-time
byAlec Gutman@chipagosfinest

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for chipagosfinest/just-fucking-cancel.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Just Fucking Cancel" (chipagosfinest/just-fucking-cancel) from ClawHub.
Skill page: https://clawhub.ai/chipagosfinest/just-fucking-cancel
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install just-fucking-cancel

ClawHub CLI

Package manager switcher

npx clawhub@latest install just-fucking-cancel
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Skill claims to analyze transactions and produce cancel URLs. All declared runtime inputs (CSV upload or optional Plaid credentials) are appropriate and proportional to that purpose. The included references/common-services.md provides cancel URLs which is expected for this use case.
Instruction Scope
SKILL.md instructs local CSV processing by default and describes Plaid as an optional remote data source; it does not instruct the agent to read unrelated system files or exfiltrate data. It explicitly states 'No automated cancellation' and that users navigate to cancel URLs manually, which fits the described workflow.
Install Mechanism
This is an instruction-only skill with no install spec and no code executed at install time. The included HTML template and reference markdown are static assets — no downloads or archive extracts are requested.
Credentials
No required environment variables are listed in the registry metadata. SKILL.md documents three optional Plaid env vars (PLAID_CLIENT_ID, PLAID_SECRET, PLAID_ACCESS_TOKEN) which are appropriate for the optional Plaid integration. Because these are highly sensitive, only supply them if you trust the hosting/agent environment and you understand that Plaid will be contacted.
Persistence & Privilege
The skill is not marked always:true, does not request persistent system modifications, and contains no instructions to change other skills' configs or system-wide settings.
Assessment
This skill appears to do what it says: analyze transaction CSVs locally and optionally pull transactions via Plaid. Recommended actions before installing or using: - Prefer the CSV workflow (local only) if you want to avoid sending financial data to third parties. - If you enable Plaid, only provide PLAID_CLIENT_ID / PLAID_SECRET / PLAID_ACCESS_TOKEN when you trust the agent host and understand Plaid will be contacted; these tokens are sensitive and grant access to account transactions. - Note a small documentation mismatch: PUBLISH.md mentions 'Browser automation for cancellations' while SKILL.md emphasizes no automated cancellation — confirm behavior before trusting any automatic cancellation actions. - Review the cancel URLs in references/common-services.md yourself; check for correctness and avoid clicking links you don't recognize. - The HTML template contains client-side JS (clipboard operations, privacy toggles). Running the report in a browser will execute that script locally; it does not appear to contact remote endpoints, but avoid pasting secrets into the report. - If you need higher assurance, ask the publisher for runtime code or a canonical upstream repo (the SKILL.md attributes an upstream GitHub project).

Like a lobster shell, security has layers — review code before you run it.

budgetingvk9782xkc83a0qkfx17cy6y9vb180ys7xcancelvk9782xkc83a0qkfx17cy6y9vb180ys7xfinancevk9782xkc83a0qkfx17cy6y9vb180ys7xlatestvk9782xkc83a0qkfx17cy6y9vb180ys7xmoney-savingvk9782xkc83a0qkfx17cy6y9vb180ys7xpersonal-financevk9782xkc83a0qkfx17cy6y9vb180ys7xplaidvk9782xkc83a0qkfx17cy6y9vb180ys7xrecurring-chargesvk9782xkc83a0qkfx17cy6y9vb180ys7xsubscriptionsvk9782xkc83a0qkfx17cy6y9vb180ys7x
2.6kdownloads
2stars
3versions
Updated 15h ago
v1.2.0
MIT-0

Just Fucking Cancel

Analyze transactions, categorize subscriptions, generate HTML audit, help cancel.

How It Works

This skill analyzes your transaction history to find recurring charges (subscriptions), helps you categorize them, and provides direct cancel URLs. No automated cancellation - you control every action.

Transaction Data → Pattern Detection → User Categorization → HTML Audit → Cancel URLs

Triggers

  • "cancel subscriptions", "audit subscriptions"
  • "find recurring charges", "what am I paying for"
  • "subscription audit", "clean up subscriptions"

Data Sources

Option A: CSV Upload (Recommended - Fully Local)

Upload a transaction CSV from your bank. All processing happens locally - no data leaves your machine.

Supported formats:

  • Apple Card: Wallet → Card Balance → Export
  • Chase: Accounts → Download activity → CSV
  • Amex: Statements & Activity → Download → CSV
  • Citi: Account Details → Download Transactions
  • Bank of America: Activity → Download → CSV
  • Capital One: Transactions → Download
  • Mint / Copilot: Transactions → Export

Option B: Plaid Integration (ClawdBot Only)

If you have ClawdBot with Plaid connected, transactions can be pulled automatically.

Important: This requires Plaid credentials and sends data to Plaid's servers:

  • PLAID_CLIENT_ID - Your Plaid client ID
  • PLAID_SECRET - Your Plaid secret key
  • PLAID_ACCESS_TOKEN - Access token for the bank connection

Privacy note: When using Plaid, transaction data is transmitted to Plaid's API. CSV analysis is fully local.

Workflow

1. Get Transactions

  • CSV: User uploads file, analyzed locally
  • Plaid: Pull last 6-12 months via API (requires credentials)

2. Analyze Recurring Charges

  • Detect same merchant, similar amounts, monthly/annual patterns
  • Flag subscription-like charges (streaming, SaaS, memberships)
  • Calculate charge frequency and total annual cost

3. Categorize with User

For each subscription, ask user to categorize:

  • Cancel - Stop immediately
  • Investigate - Needs decision (unsure, trapped in contract)
  • Keep - Intentional, continue paying

Ask in batches of 5-10 to avoid overwhelming.

4. Generate HTML Audit

Create interactive HTML report with:

  • Summary: subscriptions found, total waste, potential savings
  • Sections: Cancelled / Needs Decision / Keeping
  • Privacy toggle to blur service names
  • Dark mode support

5. Provide Cancel URLs

For each service to cancel:

  1. Look up direct cancel URL from common-services.md
  2. Provide URL to user - user navigates manually
  3. Include dark pattern warnings and tips

No automated browser interaction - this skill provides URLs and guidance only. You control the actual cancellation.

HTML Structure

Three sections, auto-hide when empty:

  • Cancelled (green badge, strikethrough) - Done items
  • Needs Decision (orange badge) - Has checkboxes for selection
  • Keeping (grey badge) - Reference only

Features:

  • Floating copy button for selected items
  • Privacy toggle blurs service names
  • Collapsible sections
  • Dark mode support

Cancellation Tips

See common-services.md for:

  • Direct cancel URLs for 50+ services
  • Dark pattern warnings (gym contracts, phone-only)
  • Retention script responses
  • Credit card dispute backup

Privacy Summary

Data SourceWhere ProcessedData Leaves Device?
CSV UploadLocal onlyNo
Plaid APIPlaid serversYes (to Plaid)

Related

  • plaid - Bank account connection
  • ynab - Budget tracking
  • copilot - Financial insights

Comments

Loading comments...