skills/whq25/rawgenai/agent-gen-image/Gen Agent Trust Hub

agent-gen-image

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates image generation tasks by executing the rawgenai CLI utility with various provider-specific arguments and subcommands.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the rawgenai tool via a Homebrew tap (WHQ25/tap/rawgenai). This is an external dependency hosted by the skill author and is considered a legitimate vendor resource within the analysis context.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it interpolates user-provided text directly into shell commands for the rawgenai tool.
  • Ingestion points: User prompts and reference image file paths provided during interaction.
  • Boundary markers: Prompts are generally enclosed in double quotes within the CLI command templates.
  • Capability inventory: The rawgenai tool interacts with external AI provider APIs and performs file system operations to save generated images.
  • Sanitization: The instructions do not describe any explicit input sanitization or validation before passing user content to the command-line interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:09 PM