The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from repository files such as AGENTS.md and CONTEXT.md to inform its domain vocabulary interview. These files represent a potential surface for indirect prompt injection if they contain untrusted content.
Ingestion points: The skill reads AGENTS.md, CONTEXT.md, and CONTEXT-MAP.md from the local file system.
Boundary markers: The instructions do not specify the use of delimiters or specific safety instructions when processing the content of these files.
Capability inventory: The skill is capable of writing to the file system (CONTEXT.md) and prompting the user via AskUserQuestion.
Sanitization: There is no explicit sanitization of the content retrieved from the files before it is used to drive the agent's logic.

ubiquitous-language