spritecook-generate-sprites

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill mentions a setup command npx spritecook-mcp setup and provides links to the official website spritecook.ai for configuration and documentation. These resources are associated with the skill's author and represent standard installation procedures for the intended service.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes tools like generate_game_art and generate_character that ingest user-provided text prompts, creating a standard input surface for data processed by the agent.
  • Ingestion points: prompt parameter in generate_game_art, generate_character, and generate_character_animations (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used for the input prompts.
  • Capability inventory: Image generation, asset polling, and file management/upload via the SpriteCook MCP server.
  • Sanitization: No explicit sanitization, escaping, or validation of the prompt content is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 12:50 AM