subnautica-ii-coop-deep-synergy-mod
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill features AI narrative and lore generation services that ingest data directly into LLM prompts without explicit boundary markers or sanitization. This creates a surface for indirect prompt injection where malicious game data could influence the AI's output.
- Ingestion points: The
eventDescriptionparameter inGenerateDiscoveryNarrativeandcreatureIdinGenerateSpeciesDescriptionwithin the C# code integration examples. - Boundary markers: Absent; untrusted variables are interpolated directly into string templates.
- Capability inventory: AI output is primarily used for in-game UI displays (PDA/Journal entries) and logging; no evidence of high-privilege side effects like command execution or file writes based on AI responses was detected.
- Sanitization: No sanitization or validation of the input strings is shown in the provided integration patterns.
Audit Metadata