unreal-fab-assets

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external marketplace listings and user-provided search queries.
  • Ingestion points: The query parameter in scripts/prepare_free_asset_acquisition.py and listing metadata (such as titles, publishers, and licenses) fetched from the Fab marketplace service.
  • Boundary markers: The instructions in SKILL.md require the agent to present listing details to the user and obtain explicit "task-scoped user approval" before taking actions like acquiring listings, accepting EULAs, or adding content to the project.
  • Capability inventory: The skill has the ability to interact with the Unreal Engine UI via the ui-control dependency and perform filesystem/Content Browser operations through the unreal-assets dependency.
  • Sanitization: Input validation is performed on the listing_id in scripts/_fab.py, where it is normalized using the standard uuid library to ensure it conforms to the expected format before being used in URL construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 06:49 AM