The Agent Skills Directory

[SAFE]: The skill is focused on software engineering best practices, specifically Domain-Driven Design (DDD) and Architectural Decision Records (ADR). It provides templates and guidelines for human-agent collaboration on project documentation.
[INDIRECT_PROMPT_INJECTION]: The skill involves a feedback loop where user-provided domain definitions are saved to CONTEXT.md and ADR files, which the agent then references for future context. While this creates a theoretical surface for indirect injection, the skill lacks high-risk capabilities (such as network access or shell execution) that could be exploited via this vector.
Ingestion points: User descriptions of domain terms and architectural rationale are used to populate documentation files.
Boundary markers: The templates defined in CONTEXT-FORMAT.md and ADR-FORMAT.md do not implement specific security delimiters or warnings against embedded instructions in the generated content.
Capability inventory: The skill is limited to reading and writing Markdown files (CONTEXT.md, CONTEXT-MAP.md, and ADR files) within the repository structure.
Sanitization: There is no explicit requirement for the agent to sanitize or validate the content provided by the user before writing it to the project files.

domain-modeling