Skills
skills/sumsubstance/agent-skills/sumsub-create-cross-check-preset/Gen Agent Trust Hub

sumsub-create-cross-check-preset

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local helper scripts (get_cross_check_preset.sh, patch_cross_check_preset.sh, and post_cross_check_preset.sh) which perform authenticated network requests to the Sumsub API.
  • [CREDENTIALS_UNSAFE]: The skill requires authentication via the SUMSUB_APP_TOKEN and SUMSUB_SECRET_KEY environment variables. It implements a safety check to ensure only sandbox tokens (prefixed with 'sbx:') are used unless explicitly overridden, and it provides clear instructions to the agent to prevent the disclosure of the secret key.
  • [SAFE]: Network communication is restricted to the official Sumsub API domain (api.sumsub.com) for the legitimate purpose of configuring document comparison rules.
  • [SAFE]: The build_cross_check_preset.py script validates user-supplied JSON or YAML input, ensuring that the title, description, and settings conform to expected types and enumeration values before generating the final API payload.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:59 PM
Security Audit — agent-trust-hub — sumsub-create-cross-check-preset