unity-multiplayer-services
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch a machine-readable documentation index from Unity's official site (docs.unity.com) to provide accurate SDK information. As this targets a well-known service for documentation purposes, it is documented neutrally and does not contribute to verdict escalation.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it ingests and processes untrusted project data to perform its functions.
- Ingestion points: The agent is directed to read local files such as manifest.json, packages-lock.json, and internal project networking scripts to establish context for its recommendations.
- Boundary markers: No specific instructions were identified that require the agent to use boundary markers or delimiters when processing content from these external project files.
- Capability inventory: The skill provides instructions for the agent to generate C# source code and suggest modifications to Unity project configuration and deployment assets.
- Sanitization: There are no explicit sanitization or validation protocols defined for content retrieved from the local environment before it is used in the prompt context.
Audit Metadata