gpt-image-edit
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents the use of the official RunComfy CLI tool and its associated API endpoints (
model-api.runcomfy.net,runcomfy.com). These are established vendor resources. - [SAFE]: Secret management instructions follow best practices, recommending the use of environment variables (
RUNCOMFY_TOKEN) or configuration files with restricted permissions (0600) for API tokens. - [SAFE]: The skill explicitly identifies the risk of indirect prompt injection from processing external image URLs and implements a 2 GiB download cap to prevent resource exhaustion attacks.
- [SAFE]: No obfuscation, unauthorized data exfiltration, or malicious prompt injection patterns were detected.
Audit Metadata