xb-add-interactions
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Indirect Prompt Injection Surface]: The skill guides the agent in generating interaction logic based on user-provided intents and action inventories. This architectural pattern represents a surface for indirect prompt injection, as malicious instructions could be embedded in the data the skill processes to influence the implementation.
- Ingestion points: User-provided interaction requirements and intent inventories defined in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to disregard embedded commands in the input data.
- Capability inventory: The skill facilitates the generation of interaction handlers, state transitions, and test cards used to implement application logic.
- Sanitization: No sanitization or validation protocols are specified for the external interaction descriptions.
- [External Package Reference]: The skill incorporates the
@dimforge/rapier3d-simd-compatlibrary to handle physics-driven behaviors such as collisions and forces. This is a recognized third-party library for the Rapier physics engine and is used as intended for the skill's functionality.
Audit Metadata