test-driven-development
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong imperative directives to enforce behavioral compliance, such as "Delete it. Start over" and "Delete means delete". These instructions could be interpreted by an agent as a command to physically remove files or work from the workspace, leading to unintended data loss.
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands (e.g.,
npm test) to verify implementation behavior. This represents an execution surface for any code or test script residing in the environment. - Ingestion points: Local source code and test files processed during the TDD cycle.
- Boundary markers: Absent; there are no delimiters or instructions to treat the code being tested as untrusted data.
- Capability inventory: Shell command execution via
npm testin SKILL.md. - Sanitization: Absent; the skill does not implement validation or sanitization of the code before triggering the test runner.
Audit Metadata