initialize-ai-navigation

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interprets natural language user requests to generate Unity C# code and modify project manifests, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: User input describing navigation requirements (e.g., 'add pathfinding', 'patrol between points') as outlined in the Routing Logic table in SKILL.md.\n
  • Boundary markers: Absent; there are no specific instructions to delimit or escape user-provided strings within the generated code.\n
  • Capability inventory: Modification of the Packages/manifest.json file and execution of C# code blocks via the Editor's eval functionality.\n
  • Sanitization: No sanitization or validation of user input is described before it is used to generate functional code snippets or project changes.\n- [DYNAMIC_EXECUTION]: The skill provides guidelines and specific code recipes in references/navigation-system.md for generating and executing C# statement blocks in the Unity Editor using eval. This is intended for environment inspection and character control.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the com.unity.ai.navigation package from the official Unity registry (https://packages.unity.com), which is a well-known and trusted service.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 02:55 PM
Security Audit — agent-trust-hub — initialize-ai-navigation