The Agent Skills Directory

[SAFE]: The skill serves as a technical guide for LangGraph state management. It utilizes official LangChain packages and standard persistence patterns for development and production environments.
[INDIRECT_PROMPT_INJECTION]: The skill defines a state schema that processes message arrays, which is a standard entry point for conversational data. While this represents a data ingestion surface, it is the intended primary purpose of the skill.
Ingestion points: The messages array in the StateSchema defined in SKILL.md captures external message content.
Boundary markers: Absent. The provided code examples do not demonstrate the use of delimiters to isolate user-provided text from agent instructions.
Capability inventory: The skill includes database write capabilities through SqliteSaver and PostgresSaver implementations.
Sanitization: Absent. The snippets show direct state updates ([...state.messages, "Bot response"]) without input validation or escaping, which is typical for simplified educational examples.

langgraph-persistence