sumsub-create-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill translates user-provided flowchart descriptions and policies into workflow payloads for the Sumsub API.\n
  • Ingestion points: Workflow routing descriptions and flowchart-style descriptions provided by the user (as described in SKILL.md).\n
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potentially malicious content embedded in the user's workflow descriptions.\n
  • Capability inventory: The skill can perform network POST and PUT requests to create and publish workflows via scripts/workflow_api.py.\n
  • Sanitization: scripts/build_workflow.py performs basic validation of node types, operators, and literal lengths, but does not sanitize the content of logic expressions.\n- [COMMAND_EXECUTION]: The skill uses Python's subprocess module and shell scripts to execute system utilities for its operations.\n
  • Evidence: scripts/workflow_api.py uses subprocess.run to execute curl commands.\n
  • Evidence: scripts/post_workflow.sh and scripts/publish_workflow.sh use shell commands for HMAC-SHA256 signing via openssl and data transmission via curl.\n- [EXTERNAL_DOWNLOADS]: The skill interacts with external API endpoints to manage workflows.\n
  • Evidence: Requests are sent to api.sumsub.com for state retrieval, validation, and publishing.\n
  • Note: This is a vendor-owned resource associated with the skill author, Sumsub.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 09:03 PM
Security Audit — agent-trust-hub — sumsub-create-workflow