atb-csv-testcase-generator
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates within a controlled developer environment using local paths provided by the user. Commands used for path validation and test execution are scoped to the intended functionality of managing operator tests.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local source code to generate test logic, which represents a potential indirect injection surface.
- Ingestion points: Operator source code (.cpp) files within the local ATB repository (Step 2).
- Boundary markers: None explicitly defined for the file read operations.
- Capability inventory: The skill utilizes Write, Edit, and Bash tools to create configuration files and execute tests.
- Sanitization: The risk is addressed via mandatory Human-in-the-Loop checkpoints (Gate 2) and a required automated Reviewer Agent audit (Step 7) before output is finalized.
Audit Metadata