sumsub-integrate-travel-rule

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a suite of Bash scripts that utilize curl to interact with the Sumsub API. These scripts facilitate tasks such as finalizing transactions, confirming ownership, and searching for existing transaction records using HMAC authentication.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles transaction data from external sources, which is a standard requirement for its integration purpose.
  • Ingestion points: Data enters the agent's context through webhook notifications and API responses fetched in examples/answer-incoming-request.js and various shell scripts.
  • Boundary markers: The implementation does not use specific delimiters to isolate external data fields such as memo or accountId from agent instructions.
  • Capability inventory: The skill utilizes Bash and curl to perform network operations and local script execution.
  • Sanitization: The scripts facilitate direct interaction with the vendor API; while they do not include explicit input sanitization in the snippets, they operate within the context of a controlled API integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:17 AM
Security Audit — agent-trust-hub — sumsub-integrate-travel-rule