Skills
skills/tul-sh/skills/flux-image/Gen Agent Trust Hub

flux-image

Fail

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The documentation contains the command curl -fsSL https://cli.inference.sh | sh. This downloads and executes a script from a remote server without verification, presenting a significant security risk if the source or connection is compromised.
  • [EXTERNAL_DOWNLOADS]: The skill downloads a binary CLI tool from dist.inference.sh during the installation phase.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to run the infsh command for image generation and system interaction.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its image generation interface.
  • Ingestion points: Untrusted data enters via the prompt and image_url fields in the JSON input to the infsh command.
  • Boundary markers: No markers are used to separate user-provided content from instructions.
  • Capability inventory: The skill can execute shell commands via Bash(infsh *) and perform network operations.
  • Sanitization: No input validation or escaping is applied to the data before it is passed to the shell.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 4, 2026, 12:29 PM