The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to run tests using standard development tools such as pytest, vitest, go test, rspec, and rails test. These operations are fundamental to the skill's purpose of automating a TDD workflow and are constrained to standard testing frameworks.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests external data in the form of feature requirements and development plans to generate test cases and implementation code.
Ingestion points: The skill reads requirements and plans in the Setup phase of SKILL.md.
Boundary markers: The instructions do not specify any delimiters or safety warnings for the ingested requirements.
Capability inventory: The skill has the capability to execute arbitrary shell commands via the Bash tool and write to the local file system.
Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is processed by the agent.

tdd-workflow