The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill recommends the installation of the deepagents npm package and various @langchain model provider packages. These dependencies originate from the LangChain ecosystem, which is a recognized and established framework for AI application development.
[DATA_EXFILTRATION]: The skill implements context management strategies that involve reading from and writing to the local file system (e.g., read_file, write_file). These operations are documented as a means to manage long-running tasks and prevent context window overflow, aligning with the primary functionality of the 'deepagents' library.
[PROMPT_INJECTION]: The skill facilitates the ingestion of data from external files. This creates a surface for indirect prompt injection, where malicious instructions embedded in processed files could attempt to influence the agent's behavior during runtime.

deep-agents