Leo CSV Stats Analyzer

Analyzes any CSV file and returns row count, column names, and basic statistics for numeric columns.

Security Scan

The skill is internally consistent with its description — it runs a small local Python script that reads a CSV and prints basic statistics — there is no code that exfiltrates data or accesses unrelated credentials; however, there are minor inconsistencies around runtime dependencies that you should verify before running.

Purpose & Capability

Name/description match the included code: analyzer.py reads a CSV and prints row/column counts and numeric stats. The included sample CSV aligns with the stated purpose.

Instruction Scope

SKILL.md limits actions to running the helper script and returning its output. The script only reads the provided CSV and prints stats; it does not read other files, env vars, or contact external endpoints. Note: SKILL.md asks the agent to present output with emojis/formatting, which the script already produces.

Install Mechanism

There is no install spec (lowest risk). However SKILL.md instructs running via 'uv run --with pandas', implying the runtime must provide the 'uv' runner and pandas. The registry metadata did not list required binaries or dependencies, so you should confirm your environment provides 'uv' and pandas or understand how 'uv run' resolves/installs packages.

Credentials

The skill requests no environment variables, credentials, or config paths. The script does not access secrets or unrelated system configuration.

Persistence & Privilege

always is false and user-invocable is true. The skill does not request permanent presence or modify other skills or system settings.

Assessment

This skill appears to be what it claims: a small local CSV analyzer. Before installing/running: 1) Confirm your agent/runtime provides or trusts the 'uv' runner and understand what 'uv run --with pandas' does in your environment (does it download packages or run untrusted code?). 2) Ensure pandas is available or that automatic installs are acceptable. 3) Only run the skill on CSVs you are willing to expose to the agent — the script prints file contents-derived statistics and could reveal sensitive data in those outputs. 4) Note the minor metadata mismatch: SKILL.md lists 'uv' as a required binary and the script needs pandas, but the registry metadata didn't declare those; verify runtime dependencies before use.

Usage

Invoke with: /csv-stats-analyzer <path-to-csv-file>

Example: /csv-stats-analyzer ./sales.csv

Features

• Shows total rows and columns
• Lists all column names
• Calculates min, max, and average for every numeric column

Rules

• The CSV must exist and be readable.
• Use the helper script at {baseDir}/analyzer.py
• Run it with: uv run --with pandas {baseDir}/analyzer.py [csv-path]
• Return the output in a clean, readable format with emojis.
• Never modify the original CSV file.