zoom-video-sdk-unity

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Video SDK sessions, specifically through fields like userName and sessionName as seen in examples/session-join-pattern.md.
  • Ingestion points: Data enters the Unity environment via zoomSdk.JoinSession and event callbacks such as HandleSessionJoin.
  • Capability inventory: The skill is designed to map these inputs to Unity scene objects and UI elements.
  • Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat these external strings strictly as data rather than instructions.
  • Sanitization: The provided examples do not include sanitization or validation logic for display names or session identifiers, which could allow maliciously crafted strings to influence agent behavior if processed in a conversational context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:55 PM
Security Audit — agent-trust-hub — zoom-video-sdk-unity