game-design-one-page-design-doc
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands to install the 'reportlab' dependency and run the local rendering script 'scripts/render_one_page_gdd.py'. The script processes user-defined JSON data and writes output files to the workspace.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate game design documents, creating a potential surface for indirect injection.
- Ingestion points: User-provided game descriptions and mechanics collected in SKILL.md.
- Boundary markers: Absent; no specific instructions are provided to delimit user input from agent instructions.
- Capability inventory: The skill writes to the local filesystem and executes shell commands for rendering.
- Sanitization: Absent; the skill does not explicitly filter or escape user content before interpolation into the output documents.
Audit Metadata