novelai-cli
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to drive the
novelai-image-mcpcommand-line interface for image generation, upscaling, and transformation tasks. - [EXTERNAL_DOWNLOADS]: Instructions provide standard methods for installing the tool from PyPI (
pip install novelai-image-mcp) or running it viauvx. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts which are passed as arguments to the CLI subcommands.
- Ingestion points: The
--promptargument in thegenerate,director colorize, anddirector emotionsubcommands in SKILL.md. - Boundary markers: Examples demonstrate the use of standard shell quoting for prompt strings to prevent command injection, though no explicit delimiters for user data are defined.
- Capability inventory: Shell command execution of the
novelai-image-mcpCLI tool. - Sanitization: No explicit sanitization or filtering of prompt content is described; the skill relies on the execution environment's handling of command-line arguments.
Audit Metadata