rank-clients-by-ltv

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's official MCP endpoint at https://api.wellapp.ai/v1/mcp to access financial records. This is a standard integration for providing the skill's primary functionality via the author's infrastructure.
  • [PROMPT_INJECTION]: The skill processes external financial data, creating a surface for indirect prompt injection. However, the agent's capabilities are limited to read-only tool calls provided by the vendor.
  • Ingestion points: Data is ingested from the invoices, workspaces, and workspace_connectors roots via well_query_records (SKILL.md).
  • Boundary markers: The skill does not explicitly define delimiters for untrusted data in the prompt.
  • Capability inventory: The skill uses only vendor-specific well_* MCP tools. It does not request shell access, file-writing permissions, or arbitrary network capabilities.
  • Sanitization: No specific sanitization or filtering logic is mentioned for the retrieved record fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 09:26 AM
Security Audit — agent-trust-hub — rank-clients-by-ltv