The Agent Skills Directory

[DYNAMIC_EXECUTION]: The core ingestion script scripts/ingest.js dynamically loads and executes JavaScript files provided via the --transform command-line argument. It attempts an ES module import() and falls back to a CommonJS require(). While this is the primary mechanism for users to provide custom transformation logic, it enables the execution of arbitrary local JavaScript code within the agent's environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from untrusted external files (JSON, CSV, Parquet, and Arrow formats) or via standard input. This behavior represents a vulnerability surface where malicious instructions embedded in the source data could be persisted to a database and potentially influence subsequent agent actions.
Ingestion points: Data is ingested via the --file argument or the --stdin flag in scripts/ingest.js.
Boundary markers: None. The skill does not use delimiters or provide instructions to the agent to ignore content within the data streams.
Capability inventory: The skill performs file system reads, network operations (to Elasticsearch nodes), and dynamic code execution via transformation scripts.
Sanitization: No sanitization or validation of the ingested data content is performed by the skill itself.
[COMMAND_EXECUTION]: The skill operates as a CLI tool that performs extensive network communication with Elasticsearch clusters and handles local file system I/O for data processing.

es-ingest