test-driven-development
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a cycle where the agent executes tests on project code, creating a surface where instructions embedded in test files could influence agent behavior. ● Ingestion points: User-provided production code and unit test files (referenced throughout SKILL.md). ● Boundary markers: None identified; the instructions do not include specific delimiters or warnings to ignore embedded content in user files. ● Capability inventory: Execution of arbitrary local code via the 'npm test' shell command (SKILL.md). ● Sanitization: No sanitization or validation of file content is performed prior to test execution.
- [COMMAND_EXECUTION]: The skill utilizes shell commands ('npm test') to verify implementation correctness as part of the primary TDD methodology.
Audit Metadata