The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze external data from the project codebase and documentation, creating an indirect prompt injection surface.
Ingestion points: Reads source code from the src/ directory and documentation files like GLOSSARY.md and GLOSSARY-MAP.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the ingested data are specified.
Capability inventory: The skill has the capability to read project files and write to GLOSSARY.md and Architectural Decision Records in the docs/adr/ directory.
Sanitization: No content validation or sanitization process is described for the information extracted from the codebase.
[NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata; no executable scripts, binary files, or dependencies were included in the package.

domain-modeling