The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific documentation and user-provided terminology, creating a potential surface for indirect instructions.
Ingestion points: The skill reads content from the repository's glossary files (e.g., CONTEXT.md, GLOSSARY.md) and architectural decision records in docs/adr/.
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions that might be embedded within the project's documentation.
Capability inventory: The skill's capabilities are limited to reading and writing local markdown files for documentation. It does not perform network operations, execute shell commands, or access sensitive system configuration files.
Sanitization: The skill does not mention specific sanitization or filtering logic for the ingested documentation content.

domain-modeling