gds-test-design

Warn

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a Python script located at {project-root}/_bmad/scripts/resolve_customization.py during activation and completion. This creates a dependency on executable files residing in the user's project directory.- [DYNAMIC_EXECUTION]: The workflow allows for the execution of arbitrary steps defined in configuration arrays (activation_steps_prepend and activation_steps_append). These steps are loaded dynamically from configuration files and executed by the agent, allowing for untracked logic changes.- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting untrusted external data.
  • Ingestion points: Reads game design documentation (GDD) and project context files using glob patterns (e.g., {project-root}/**/project-context.md).
  • Boundary markers: The instructions do not define boundary markers or instructions to ignore embedded commands within the ingested text.
  • Capability inventory: The skill has the capability to execute Python scripts and write markdown files to the project's output folder.
  • Sanitization: No validation or filtering of the ingested documentation content is performed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 5, 2026, 08:01 PM
Security Audit — agent-trust-hub — gds-test-design