multimodal-gen

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts generate_image.py, generate_video.py, and prompt_optimizer.py execute the local system command pass api/xingjiabiapi via subprocess.run to retrieve authentication credentials from the password manager.
  • [COMMAND_EXECUTION]: The generate.py wrapper script dynamically orchestrates the content generation workflow by executing internal Python scripts (prompt_optimizer.py, generate_image.py, generate_video.py) using subprocess.run with arguments derived from user input.
  • [EXTERNAL_DOWNLOADS]: The skill downloads resulting image and video files from remote URLs, including the s3.ffire.cc domain, using requests.get after content generation is completed by the external service.
  • [DATA_EXFILTRATION]: User-provided prompts and the retrieved API key are transmitted to the external API endpoint https://xingjiabiapi.com/v1 to perform requested tasks.
  • [PROMPT_INJECTION]: The skill ingests untrusted user input as generation prompts and interpolates them directly into API payloads and internal command execution calls without robust boundary markers or sanitization, creating a surface for indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 06:59 AM