gsp-first-playable
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user ideas and generate various project files, creating a vulnerability surface.
- Ingestion points: User ideas and prompts (SKILL.md).
- Boundary markers: No boundary markers or 'ignore' instructions are specified to handle untrusted input.
- Capability inventory: The skill is authorized to write multiple markdown files to the
docs/game-studio/directory (SKILL.md). - Sanitization: No input validation or content sanitization is described in the workflow instructions.
Audit Metadata