The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process content from external project files which could potentially contain malicious instructions.
Ingestion points: Reads docs/agents/domain.md, GLOSSARY.md, GLOSSARY-MAP.md, and CONTEXT.md to identify glossary terms and decision records.
Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the files being read.
Capability inventory: The agent is authorized to read and write files within the repository to update documentation.
Sanitization: There is no evidence of input validation or content sanitization for the data retrieved from the repository files.

domain-modeling