cardano-mcp-transactions
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted binary data (CBOR hex) provided by external sources or users.
- Ingestion points: The
submit_transactiontool accepts acborstring which can be sourced from untrusted dApp APIs or external files. - Boundary markers: The skill establishes manual boundaries by requiring a "Transaction Preview" (Rule 1) and a confirmation step (Rule 2), although these are instructions for the agent rather than programmatic enforcement.
- Capability inventory: The skill possesses the capability to broadcast transactions to the blockchain via
submit_transaction, which is a high-impact write operation involving financial assets. - Sanitization: There is no automatic validation or sanitization of the CBOR content; the skill relies on the agent's ability to decode and summarize the data accurately before the user approves it.
- [EXTERNAL_DOWNLOADS]: The skill provides an informative reference to an external GitHub repository for the Cardano MCP server (
https://github.com/IndigoProtocol/cardano-mcp). This is documented as a reference link and does not involve automated script execution or unverified binary downloads during the skill's runtime.
Audit Metadata