game-asset-core
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow for transforming user requests into image generation prompts, which constitutes a surface for indirect prompt injection.\n
- Ingestion points: User-provided descriptions for game assets are processed in
SKILL.mdto create generator prompts.\n - Boundary markers: None explicitly defined; the skill relies on a verification discipline ('Verify by describing blind') to ensure output matches the intended specification.\n
- Capability inventory: Image generation via external tools ('Imagine tools') and potential image manipulation using the Python Imaging Library (PIL).\n
- Sanitization: No explicit input filtering is described.\n- [SAFE]: No malicious patterns, such as hardcoded credentials, unauthorized command execution, or data exfiltration, were detected.\n- [SAFE]: The mention of using PIL for asset composition is a standard technical recommendation and does not involve remote code execution from untrusted sources.
Audit Metadata