comfyui-remote-asset-injection-protocol
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were found. The terminology "injection" in the skill title refers to the legitimate programmatic population of fields in a ComfyUI JSON API payload.
- [DATA_EXFILTRATION]: No sensitive file paths (such as SSH keys or environment variables) or unauthorized network exfiltration patterns were detected. The instructions involve standard ComfyUI API endpoints for workflow submission.
- [COMMAND_EXECUTION]: The skill does not contain shell commands, script execution, or requests for elevated privileges. It describes high-level logic for interacting with a remote application's API.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or other sensitive credentials are present in the documentation.
Audit Metadata