skills/anasadda/skills/flux-image/Gen Agent Trust Hub

flux-image

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation instructions and CLI configuration from the official inference.sh GitHub repository.
  • [COMMAND_EXECUTION]: Utilizes the belt command-line interface to interact with remote FLUX models for image generation and fine-tuning.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for user-provided prompts that are sent to an external model inference service.
  • Ingestion points: prompt and image_url fields within JSON payloads for the belt CLI (SKILL.md).
  • Boundary markers: Inputs are structured within JSON command arguments.
  • Capability inventory: Shell execution of the belt utility via Bash.
  • Sanitization: No local sanitization is performed on prompts; the skill relies on the safety filters of the destination AI models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:26 AM