game-development
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): Persona instructions are focused on domain expertise and do not attempt to override safety constraints.
- Data Exposure (SAFE): No access to sensitive files or hardcoded credentials detected.
- Remote Code Execution (SAFE): The skill does not install external packages or execute remote code.
- Indirect Prompt Injection (LOW): 1. Ingestion points: Processes user-provided code files (.ts, .js). 2. Boundary markers: Absent. 3. Capability inventory: No dangerous capabilities (execution/network) found. 4. Sanitization: Absent.
- Obfuscation (SAFE): No hidden or encoded content detected.
Audit Metadata