gds-agent-game-architect
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a Python script located at
{project-root}/_bmad/scripts/resolve_customization.pyto resolve configuration and persona overrides during the activation phase. - [COMMAND_EXECUTION]: The agent is instructed to execute sequences of steps defined in the
{agent.activation_steps_prepend}and{agent.activation_steps_append}configuration arrays, which facilitates dynamic behavior based on local setup. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by ingesting and acting upon content from local configuration and project files.
- Ingestion points: Data is read from
{project-root}/_bmad/custom/TOML files,{project-root}/_bmad/gds/config.yaml, and markdown files matching{project-root}/**/project-context.md. - Boundary markers: No specific delimiters are used to wrap or isolate ingested content from the system instructions.
- Capability inventory: The skill can execute local Python scripts and process dynamic activation instructions.
- Sanitization: Content from the ingested files is used directly without validation or sanitization.
Audit Metadata