skills/openclaw/skills/copilot-money/Gen Agent Trust Hub

copilot-money

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the copilot-money-cli package from the official Python package registry (PyPI) to provide its core functionality.\n- [COMMAND_EXECUTION]: Utilizes a dedicated CLI tool (copilot-money) to query financial records, list accounts, and refresh bank connections.\n- [DATA_EXFILTRATION]: Accesses personal finance data including transaction history and account balances. It retrieves authentication tokens from supported browser storage (Chrome, Firefox, Safari, Arc) and stores configuration files locally at ~/.config/copilot-money/config.json to facilitate API access.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing external data retrieved from the Copilot Money API.\n
  • Ingestion points: Financial transaction descriptions, account names, and holdings data retrieved via API calls (SKILL.md).\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are documented for the processed data.\n
  • Capability inventory: The skill can execute various CLI commands and display detailed financial information which could be influenced by injected content.\n
  • Sanitization: No sanitization or validation of the retrieved financial data is described prior to processing by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:39 AM