InvoiceTW
Analysis
The skill is mostly a local receipt tracker, but its main lottery-checking feature appears to use simulated hard-coded winning numbers while presenting results as real invoice prize checks.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
// 簡化的中獎號碼資料庫(實際應連接到財政部 API) // 這裡用隨機生成模擬
The user-facing skill describes automatic invoice winning checks, but the code itself says the winning-number database is simulated instead of connected to the official Ministry of Finance source.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
發票明細:`~/openclaw_workspace/InvoiceTW/receipts.json` 中獎記錄:`~/openclaw_workspace/InvoiceTW/wins.json` 報表:`~/openclaw_workspace/InvoiceTW/reports/`
The skill persistently stores user-entered invoice details, winnings, and reports in local workspace files.
