The Agent Skills Directory

[SAFE]: The skill is composed of purely instructional markdown documents focused on software engineering best practices. No executable scripts, unauthorized system commands, or malicious obfuscation techniques were found in any of the analyzed files.
[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to resolve and read external artifacts like ADRs and domain vocabulary. This establishes a surface for indirect prompt injection, where an attacker who can modify these project documents might attempt to influence the agent's implementation logic. However, given the context of a development assistant, this is a standard operational requirement and is considered a low-risk architectural pattern. Ingestion points: The agent is instructed to read vocabulary and ADRs via the /domain-modeling and /codebase-design interfaces as described in SKILL.md. Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the TDD guidelines. Capability inventory: The agent has the capability to write and modify source code and test files in response to the instructions. Sanitization: There are no explicit instructions for sanitizing or validating the content of the ADRs or vocabulary before use.

tdd