gds-test-design
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
uv runto execute local Python scripts (resolve_customization.py) located in the project's_bmad/scriptsdirectory for configuration resolution and completion tasks. This behavior relies on the existence and integrity of scripts within the project environment. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external game design documentation (GDD) and feature specifications, which could contain adversarial instructions intended to bypass agent constraints.
- Ingestion points: Game design documents, feature specifications, and configuration files (
.toml) located within the project directory. - Boundary markers: The skill lacks explicit boundary markers or instructions to treat documentation content as untrusted data rather than executable instructions.
- Capability inventory: The skill possesses the ability to execute local scripts via
uv runand write generated test plans to the file system. - Sanitization: There is no evidence of content filtering, validation, or sanitization applied to the game design documentation before it is processed by the agent.
Audit Metadata