comfyui-skill-openclaw

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent (SKILL.md Step 0 and the registry/client flow) to load and analyze externally-provided ComfyUI workflow JSON and schema files (data/<server_id>/workflows/... and schema.json) and to call configurable remote ComfyUI servers (config.json server URLs → /prompt, /history/{prompt_id}, /view), so untrusted/user-provided third‑party content is ingested and can directly influence which workflows are chosen and how the agent drives tool actions.