comfyui-workflows
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including workflow payloads and request results, which could contain instructions designed to influence the agent's behavior.
- Ingestion points: Workflow graphs and inputs are retrieved via
get_deployment(SKILL.md), and execution outputs are retrieved viaget_request_result(SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the ComfyUI workflow data.
- Capability inventory: The skill enables the agent to submit requests (
submit_request), cancel requests (cancel_request), and execute actions via a proxy (call_instance_proxy). - Sanitization: There are no explicit instructions for sanitizing or validating the content of the workflow schema or the resulting outputs before processing.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and workflow resources from the vendor's official website.
- Evidence: Provides links to
runcomfy.comanddocs.runcomfy.comfor workflow inspection and API documentation.
Audit Metadata