sumsub-create-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied flowchart descriptions and verification policies to generate structured API payloads for Sumsub workflows. This represents a vulnerability surface where maliciously crafted user instructions could influence the generated workflow logic.
- Ingestion points: User-provided flowchart labels and descriptions in the conversation, as described in Step 1 of the Procedure in SKILL.md.
- Boundary markers: The instructions do not require the use of explicit delimiters or safety headers when interpolating user-provided logic into the workflow spec.
- Capability inventory: The skill possesses the ability to write files via the
Writetool and perform network operations against the Sumsub API via theBashtool and accompanying scripts (post_workflow.sh,publish_workflow.sh,workflow_api.py). - Sanitization: While
build_workflow.pyperforms structural and schema validation, it does not sanitize or filter the natural language logic embedded within the workflow nodes and edges.
Audit Metadata