pixi-vn-ink-getting-started
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents a system for processing narrative content from .ink files, which represents a data ingestion surface area associated with the skill's primary function.\n
- Ingestion points: .ink source files specified in the project configuration (SKILL.md).\n
- Boundary markers: The skill relies on standard narrative parsing and does not define specific agent-level delimiters for data isolation.\n
- Capability inventory: The included Vite plugin performs file system writes to output compiled JSON narrative data (SKILL.md).\n
- Sanitization: The documentation notes that custom hashtag commands can implement zod validation for their arguments, providing a layer of input verification (SKILL.md).\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing verified project dependencies from the vendor's repository and package scope.\n
- Evidence: Installation of @drincs/pixi-vn-ink and npx skills add commands targeting DRincs-Productions/pixi-vn-ink (SKILL.md).\n- [COMMAND_EXECUTION]: Provides example commands for developer debugging that interact with the local Vite server.\n
- Evidence: curl commands targeting localhost:5173 for API introspection during development (SKILL.md).
Audit Metadata