The Agent Skills Directory

[SAFE]: The skill uses local filesystem tools (Read and Edit) to interact with documentation in the docs/sdd/ directory. These operations are within the expected scope of a development implementation tool.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it reads and processes user-controlled documentation files (docs/sdd/{change-name}/<artifact>.md) which are then used to influence the agent's code implementation logic.
Ingestion points: Artifact files read via the Read() tool from the project-local docs/sdd/ path.
Boundary markers: Absent; instructions do not explicitly mandate delimiters or safety warnings when reading these files.
Capability inventory: The skill utilizes Read() and Edit() tools for file manipulation and can invoke other technical skills.
Sanitization: Absent; the skill does not specify validation or sanitization of the content read from design artifacts.

sdd-apply