Skills Explorer Add Skills

finding-data-lake-assets

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: analysis, data, glue, s3, search.

What it does

Resolve data lake and lakehouse asset references across Glue Data Catalog, S3, S3 Tables, and Redshift. Triggers on: find the table, where is our data, which table has, locate dataset, find data for, search catalog, what tables match, Redshift table, lakehouse table, data lake table, warehouse table, reverse lookup S3 path. Do NOT use for: full catalog audits (use exploring-data-catalog), running queries (use querying-data-lake), creating tables (use creating-data-lake-table).

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill finding-data-lake-assets

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/plugins/aws-data-analytics/skills/finding-data-lake-assets ~/.claude/skills/finding-data-lake-assets

Safety box score

Grade B, low risk: 23 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a read-only resolver for AWS data lake and lakehouse metadata across Glue, S3, S3 Tables, and Redshift. The main risks are that it executes AWS CLI/MCP commands and, in a fallback path, writes and runs a Python boto3 script while sending queries to AWS services using the user's configured credentials.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)It explicitly runs AWS MCP/AWS CLI commands and, in the broad-scan fallback, says to "Write a short Python script using boto3..." and run it with `python3`.
Network access2 (moderate)It sends search and lookup requests to remote AWS services (`aws glue search-tables`, S3/S3 Tables APIs, and Redshift SQL like `SELECT ... FROM svv_all_tables`).
Filesystem reach1 (low)The fallback path writes a Python script to a file before execution; no broader file deletion or external-path access is described.
Secrets & credentials1 (low)It requires the caller's AWS auth context, including `aws sts get-caller-identity`, but does not ask for raw keys, tokens, or passwords.
Privilege & persistence0 (none)There is no sudo, global install, service registration, scheduled task creation, or OS/shell configuration change.
Instruction hijack surface0 (none)The only "ignore previous instructions" wording is about untrusted customer catalog text and is framed as data to ignore, not as a directive to the agent.
Irreversible actions0 (none)The skill only resolves and returns references; it does not deploy, publish, send messages, pay, book, or delete anything.
Transparency0 (none)All shipped content is plain markdown and readable; no binaries, hidden blobs, or downloaded installers are present.

Before installing

Rated 2026-10-20 by an automated review of 2 files from the skill's repository.

Source

Repository
aws/agent-toolkit-for-aws (all skills from this repository)
Path
plugins/aws-data-analytics/skills/finding-data-lake-assets/SKILL.md
Branch
main
Collection
aws-data-analytics
Updated
2026-09-19