Skills
Navigate
skills/xinvxueyuan/novelai-image-mcp/novelai-mcp-tools/Gen Agent Trust Hub

novelai-mcp-tools

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing user-supplied prompts, which are then used in network API calls and file operations. This creates an attack surface for indirect prompt injection if the agent retrieves untrusted content from an external source (e.g., a web page or file) and passes it into the generation prompt.
  • Ingestion points: The prompt and negative_prompt parameters in tools like generate_image, image_to_image, and inpaint within SKILL.md.
  • Capability inventory: The skill performs network operations to NovelAI API endpoints (image.novelai.net, api.novelai.net) and writes/reads PNG files to the local file system (NOVELAI_OUTPUT_DIR) as described in SKILL.md.
  • Boundary markers: There are no instructions for using delimiters or boundary markers to isolate untrusted data within the prompts.
  • Sanitization: No sanitization or validation of the prompt content is specified in the current instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 12:57 PM