comfyui-preflight
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes ComfyUI workflow JSON files which could theoretically contain malicious data. 1. Ingestion points: scripts/preflight.py reads workflow JSON files provided as command-line arguments. 2. Boundary markers: The script does not use specific delimiters or instructions to ignore embedded content within the JSON structure. 3. Capability inventory: Actions are restricted to HTTP GET requests to a user-specified URL and printing a JSON summary to standard output; no file-writing or code-execution capabilities were identified. 4. Sanitization: The script assumes valid JSON structures and does not perform additional sanitization of input data.
- [SAFE]: The script follows standard practices for developer tools, including the use of environment variables for API keys and the use of Python's standard library for all operations.
Audit Metadata