The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional content and code examples related to software testing best practices. It does not include executable scripts, external network operations, or sensitive file access.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read CONTEXT.md (if it exists) to align test names and interfaces with the project's domain language. While this is an ingestion point for external data, it is a standard practice for maintaining codebase consistency and does not present an exploitable surface in this context.
[FRONTMATTER]: The YAML frontmatter in SKILL.md and agents/openai.yaml is used correctly for platform identification and configuration without introducing security risks.

tdd