gsd-autonomous
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard automation loop (discuss, plan, execute) to manage project milestones. It operates within the expected scope of a development agent.
- [DATA_INGESTION]: The skill ingests phase instructions and state information from local project files such as
ROADMAP.mdand.planning/STATE.md. This is the primary intended function of the workflow engine. - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool and internalgsd-toolsto execute project-specific tasks. These operations are driven by the project's own configuration and are standard for a task-execution agent. - [METADATA_CONSISTENCY]: The skill's description and objective align correctly with the tools requested and the logic defined in the processing section.
Audit Metadata