flux-image

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of external dependencies and code from remote sources, including instructions to add skills from the belt-sh and inference-sh repositories via 'npx'.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the 'belt' utility to run inference models, sample inputs, and list available applications.
  • [PROMPT_INJECTION]: The skill processes untrusted user data, creating a surface for indirect prompt injection.
  • Ingestion points: The prompt and image_url parameters provided in user examples (SKILL.md).
  • Boundary markers: None; input is interpolated into a JSON string within a shell command.
  • Capability inventory: The skill has bash execution capabilities via the 'belt' CLI to perform network operations and file writes.
  • Sanitization: No input sanitization or validation logic is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:09 PM
Security Audit — agent-trust-hub — flux-image