ultimate-tdd
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands and test runners (e.g., npx jest, pytest, go test) to verify code behavior during the TDD cycle.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes project-specific files that could be controlled by an external actor.
- Ingestion points: Reads local configuration files like package.json, pyproject.toml, and CMakeLists.txt.
- Boundary markers: Absent; the skill does not use delimiters to isolate data from instructions.
- Capability inventory: The agent can execute shell commands defined in project test scripts through its test runner detection logic.
- Sanitization: Absent; the skill does not validate the content of project files before acting on them.
Audit Metadata