flux-image

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and documentation from the official inference.sh GitHub repository and website.- [COMMAND_EXECUTION]: Utilizes the belt CLI tool to authenticate with the platform and execute image generation models as intended.- [PROMPT_INJECTION]: The skill ingests user-provided text through a JSON-structured --input flag for image generation prompts. While this represents a surface for indirect prompt injection, the impact is limited to the content of the generated image and the skill uses structured data boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — flux-image