bitrefill-website
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an official API endpoint (api.bitrefill.com/v2) and an MCP (Model Context Protocol) endpoint (api.bitrefill.com/mcp) for tool integration. These are legitimate resources owned by the vendor 'bitrefill'.
- [COMMAND_EXECUTION]: Provides a configuration command for the Claude CLI (
claude mcp add --transport http bitrefill https://api.bitrefill.com/mcp) to enable automated tool usage. This is a standard setup procedure for the Model Context Protocol. - [DATA_EXFILTRATION]: No evidence of unauthorized data transmission. The skill explicitly mentions that the official API requires authentication (Bearer token or Basic auth), which is standard practice for secure service access.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from the Bitrefill API and website. While this represents a standard attack surface for indirect injection, there are no exploitable capabilities (like eval or filesystem writes) that would escalate this risk beyond a baseline level.
Audit Metadata