The Agent Skills Directory

[SAFE]: No security issues detected. The skill follows a structured workflow for financial data retrieval using authenticated tool calls to the vendor's platform.
[EXTERNAL_DOWNLOADS]: The skill connects to the vendor's official Model Context Protocol (MCP) endpoint at https://api.wellapp.ai/v1/mcp. This is a legitimate resource owned by the skill author (wellapp-ai) and is required for the skill's core functionality.
[DATA_EXFILTRATION]: Accesses sensitive financial data including customer names, outstanding balances, and invoice numbers. This data access is restricted to the user's authenticated workspace and occurs via official vendor tools. There is no evidence of data being transmitted to untrusted third-party domains.
[INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests data from external sources via well_query_records (invoices and workspace data).
- Boundary markers: The instructions do not specify the use of delimiters or specific markers when interpolating invoice data into the agent's context.
- Capability inventory: The skill is limited to data retrieval and mathematical bucketing; it lacks capabilities for arbitrary command execution, file system modification, or non-vendor network operations.
- Sanitization: No explicit sanitization of text fields (like customer names) is performed, though the skill primarily focuses on numeric values for aging calculations.

accounts-receivable-aging