subnautica-ii-deep-synergy-coop-mod

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate instructions and code samples for extending a game mod using the BepInEx framework, a standard practice in the modding community.
  • [SAFE]: Credential management instructions correctly advise users to store API keys in a .env file, which is a standard security practice for managing secrets locally.
  • [SAFE]: All external references, including the BepInEx GitHub repository and Google's STUN servers, point to well-known and reputable services.
  • [INDIRECT_PROMPT_INJECTION]: The proposed integration with OpenAI and Claude APIs for dynamic narration creates a surface where external data could potentially influence the AI's output.
  • Ingestion points: Data enters the system via peer-to-peer WebRTC channels, responses from AI APIs, and user inputs through console commands like /api_narrate.
  • Boundary markers: The provided C# code snippets do not implement explicit delimiters or system instructions to distinguish between trusted commands and untrusted narrative data.
  • Capability inventory: The skill facilitates network communication (WebRTC and HTTP) and local file operations (configuration and logs).
  • Sanitization: The documentation does not specify sanitization or validation routines for text strings sent to or received from the AI narration engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 11:44 PM