nixie-fx-runtime

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to install the nixie-fx package and its peer dependencies (three or pixi.js) using npm. This is a standard installation step for the library's functionality.
  • [EXTERNAL_DOWNLOADS]: The implementation fetches manifest and effect configuration files from a user-specified baseUrl. This is a routine operation for loading game assets and does not involve suspicious or hardcoded remote sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external JSON data from remote URLs.
  • Ingestion points: Manifest and effect JSON files are fetched in references/export-bundles.md.
  • Boundary markers: The skill uses structured schema parsing via the parseVfxExportManifest function to validate the structure of the fetched data.
  • Capability inventory: The skill's capabilities are limited to network fetching and renderer interaction; it does not have access to sensitive system resources or command execution beyond the initial installation.
  • Sanitization: External content is treated as structured data and processed by library-specific loaders rather than being directly interpolated into agent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 10:15 PM