gsd-add-tests
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a predefined workflow from a local path (
/mnt/local-analysis/workspace-hub/.codex/get-shit-done/workflows/add-tests.md). This workflow governs the classification, planning, and generation of tests. - [DATA_EXPOSURE]: The skill accesses workspace metadata and planning files such as
.planning/STATE.mdand.planning/ROADMAP.mdto establish context for test generation. - [INDIRECT_PROMPT_INJECTION]: The skill processes implementation files from the workspace as input for the test generation process. While this represents an ingestion surface for untrusted data, the skill includes manual approval gates (classification and test plan approval) and follows a restricted RED-GREEN verification process, which mitigates the risk of malicious code influencing the agent's behavior beyond the intended scope of test creation.
Audit Metadata