bestchange

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a well-defined interface for a specific financial utility. It contains no commands for local file access, credential harvesting, or unauthorized privilege escalation.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with a dedicated external endpoint https://bestchange-mcp.krutovoy.me/mcp to perform its core functions. This behavior is expected for an MCP-based exchange tool and is clearly documented.
  • [DATA_EXFILTRATION]: No exfiltration patterns were detected. The skill only transmits user-provided search terms (currency names) and amounts required for quoting exchange rates.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety guidelines, extract system prompts, or override agent constraints.
  • [COMMAND_EXECUTION]: No shell commands, script executions, or dynamic code evaluations are present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:47 AM
Security Audit — agent-trust-hub — bestchange