skills/wellapp-ai/skills/fx-exposure/Gen Agent Trust Hub

fx-exposure

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 server at https://api.wellapp.ai/v1/mcp to retrieve workspace and financial data. This is a legitimate connection required for the skill's primary function and follows standard integration patterns for the wellapp-ai platform.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from external financial records. \n
  • Ingestion points: Data is retrieved from the invoices, accounts, and account_balances roots via the well_query_records tool in SKILL.md. \n
  • Boundary markers: The instructions do not define specific delimiters or warnings to the agent to ignore instructions embedded within the record data. \n
  • Capability inventory: The skill's capabilities are restricted to read-only queries and information reporting. It lacks high-risk capabilities such as file system writes, arbitrary shell command execution, or uncontrolled network requests. \n
  • Sanitization: There is no explicit requirement for the agent to sanitize or filter the content of the financial records before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 09:26 AM
Security Audit — agent-trust-hub — fx-exposure