novelai-cli

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the novelai-image-mcp package from PyPI using pip install or execute it via uvx. This package is a vendor-owned resource associated with the author 'xinvxueyuan'.
  • [COMMAND_EXECUTION]: Provides instructions for driving the novelai-image-mcp CLI tool to interact with the NovelAI API for tasks such as image generation, upscaling, and transformation.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface where user-supplied prompts are interpolated into shell commands. 1. Ingestion points: The --prompt and --negative flags for the generate, colorize, and emotion subcommands. 2. Boundary markers: Absent. 3. Capability inventory: Shell execution of the novelai-image-mcp CLI. 4. Sanitization: Absent in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 05:31 PM
Security Audit — agent-trust-hub — novelai-cli