game-design-core
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious patterns detected across all threat categories. The skill is entirely composed of markdown instructions and references to local documentation.- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were identified.- [INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses an ingestion surface as it processes user input using local reference files (
references/patterns.md,references/sharp_edges.md,references/validations.md). However, since the skill has no capability to execute code, write to the filesystem, or access the network, the risk of exploitation is negligible. Evidence Chain: 1. Ingestion points: references/*.md via prompt interpolation. 2. Boundary markers: Absent. 3. Capability inventory: None (no code or subprocesses). 4. Sanitization: Absent.
Audit Metadata