comfyui-node-outputs
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates processing external workflow metadata and text, which serves as a potential surface for indirect prompt injection.\n- Ingestion points: Workflow data enters the agent context via
io.String.Input,io.Hidden.prompt, andui.PreviewTextinSKILL.md.\n- Boundary markers: There are no explicit markers or instructions to delimit or ignore instructions embedded in ingested data.\n- Capability inventory: The skill possesses file-writing capabilities throughpil_image.saveand the helper classes, as well as UI rendering components.\n- Sanitization: No sanitization or filtering of external content is documented before it is stored or rendered.
Audit Metadata