dodo-mcp-usage

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions direct the user to run npx -y dodopayments-mcp@latest and npx -y mcp-remote@latest to execute MCP servers. These packages originate from the vendor's official ecosystem or represent standard utility tools for the MCP protocol.
  • [DYNAMIC_EXECUTION]: The skill describes an execute tool that runs TypeScript code against the Dodo Payments SDK. According to the documentation, this execution is performed in an isolated sandbox to mitigate risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves processing data from external sources, which constitutes a potential attack surface:
  • Ingestion points: Documentation search results from dodo-knowledge and live account data (products, subscriptions, customers) from the dodopayments-api server in SKILL.md.
  • Boundary markers: The skill does not define specific technical delimiters for input data but provides high-level guidance for users to confirm operations.
  • Capability inventory: The execute tool provides programmatic access to the Dodo Payments API, which is utilized for reading and writing financial data.
  • Sanitization: The instructions recommend returning trimmed summaries rather than full objects to limit data exposure in the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 12:31 PM