gds-agent-game-designer
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script (
resolve_customization.py) within the project root to merge configuration settings. This script is part of the project's infrastructure and is used for initialization. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data. Ingestion points:
{project-root}/_bmad/gds/config.yaml,{project-root}/_bmad/custom/{skill-name}.toml, and files specified in{agent.persistent_facts}(SKILL.md). Boundary markers: Absent. Capability inventory: Subprocess calls viauv run(SKILL.md), file reading, and skill dispatching. Sanitization: Absent. - [DYNAMIC_EXECUTION]: The skill uses dynamic variables and runtime script execution to establish the agent's identity and capabilities, consistent with the framework's design.
Audit Metadata