skills/smithery/ai/game-developer/Gen Agent Trust Hub

game-developer

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE] (INFO): The skill consists entirely of markdown instructions and metadata. No executable scripts, binaries, or automated tasks are included for analysis.
  • [INDIRECT_PROMPT_INJECTION] (LOW): Ingestion points: The 'Analyze requirements' step in the Core Workflow processes untrusted user-provided game specifications. Boundary markers: No delimiters or instructions to ignore embedded commands are present. Capability inventory: The skill is restricted to generating code and architectural advice; it lacks direct tool execution or system modification capabilities. Sanitization: No input validation or sanitization is specified. Severity: LOW because the capability is limited to influencing the agent's reasoning and text output.
  • [PROMPT_INJECTION] (SAFE): No attempts to override system prompts or bypass safety guidelines were detected.
  • [DATA_EXFILTRATION] (SAFE): No hardcoded credentials or instructions to access and exfiltrate sensitive files were found.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:44 AM
Security Audit — agent-trust-hub — game-developer