implement-with-tdd
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied specification files or change descriptions, which could contain adversarial instructions. \n
- Ingestion points: Reads files or content from the
$ARGUMENTSvariable defined inSKILL.md. \n - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content solely as data. \n
- Capability inventory: Includes file system write access for source and test code, and shell execution for running test suites. \n
- Sanitization: No input validation or sanitization is performed on the ingested data.\n- [DYNAMIC_EXECUTION]: The core loop involves the generation and execution of code within the project environment. \n
- Evidence:
SKILL.mdinstructs the agent to write implementation and test code to the repository and execute it using the project's test runner.\n- [COMMAND_EXECUTION]: The skill requires executing local commands to manage the development process. \n - Evidence: Executing test commands and
git diff --statas part of the loop and budgeting process.
Audit Metadata