test-driven-development
Warn
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses rigid and directive language to enforce behavior, specifically the instructions "Delete means delete" and "Write code before the test? Delete it. Start over." These commands could override the agent's general safety guidelines regarding data preservation and lead to the permanent deletion of legitimate user work.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands such as
npm teston the host system to verify code behavior. - [DYNAMIC_EXECUTION]: The core TDD workflow involves the agent generating new source code and immediately executing it to verify tests, which is a form of dynamic script generation and execution.
Audit Metadata