The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's setup instructions in SKILL.md include a command to download and execute a script from https://elastic.co/start-local. This is used to provision a local Elasticsearch environment using official vendor infrastructure.
[COMMAND_EXECUTION]: The scripts/ingest.js tool implements a custom transformation feature that dynamically loads and executes JavaScript files from the local file system. It uses import() and require() to load paths specified via the --transform command-line argument, allowing for the execution of user-provided logic during data processing.
[DATA_EXFILTRATION]: The skill manages sensitive Elasticsearch authentication data, such as API keys and passwords. These credentials are accepted via environment variables or plaintext command-line flags to authenticate the tool with target Elasticsearch clusters.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from external sources like CSV, JSON, and Parquet files.
Ingestion points: scripts/ingest.js (via --file or --stdin flags).
Boundary markers: None identified; external data is processed directly.
Capability inventory: scripts/ingest.js performs network operations to Elasticsearch clusters and reads local files.
Sanitization: No explicit sanitization or instruction-filtering is performed on the ingested content before it is transformed and indexed.

elasticsearch-file-ingest