The Agent Skills Directory

[SAFE]: The skill provides legitimate guidance for software development practices. The instructions and code examples for the TDD cycle are standard for the industry and do not contain any malicious patterns, obfuscation, or data exfiltration attempts.
[INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent creates code and tests based on external requirements, creating a surface for indirect injection if a user provides malicious specifications.
Ingestion points: User-provided functional requirements and test scenarios (SKILL.md).
Boundary markers: Absent; the skill does not define specific delimiters for separating user-provided data from agent instructions.
Capability inventory: The skill leverages Bash, Write, and Edit tools to generate code and execute test commands (SKILL.md).
Sanitization: Absent; the skill relies on the agent's core safety logic for sanitizing generated code based on user input.

tdd