gds-test-automate
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script
{project-root}/_bmad/scripts/resolve_customization.pyusing theuv runcommand during both the activation phase (Step 1) and the completion phase (Step 5). These executions are used to resolve workflow configuration and final instructions. - [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data from the game project to generate test code, which presents a surface for indirect prompt injection.
- Ingestion points: The skill reads project-level configuration files (
config.yaml,.tomlcustomization files) and the game's source code (logic classes, state machines, and data structures) located in the project root. - Boundary markers: The instructions do not define specific boundary markers or delimiters when interpolating analyzed code into the test generation templates.
- Capability inventory: The skill is capable of writing multiple files to the local filesystem (unit, integration, and smoke tests) and executing local scripts via the shell.
- Sanitization: There is no explicit mention of sanitization, validation, or escaping of the ingested source code content before it is used to generate the output test files.
Audit Metadata