Automatically analyzes CSV files and generates comprehensive insights with visualizations without requiring user prompts Download the free CSV Data Summarizer skill for Claude Code, Codex CLI, and other AI coding tools.
SaferSkills independently audited CSV Data Summarizer (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 2 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This Skill analyzes CSV files and provides comprehensive summaries with statistical insights and visualizations.
Claude should use this Skill whenever the user:
DO NOT ASK THE USER WHAT THEY WANT TO DO WITH THE DATA. DO NOT OFFER OPTIONS OR CHOICES. DO NOT SAY "What would you like me to help you with?" DO NOT LIST POSSIBLE ANALYSES.
IMMEDIATELY AND AUTOMATICALLY:
THE USER WANTS A FULL ANALYSIS RIGHT AWAY - JUST DO IT.
The skill intelligently adapts to different data types and industries by inspecting the data first, then determining what analyses are most relevant.
Example adaptations:
✅ CORRECT APPROACH - SAY THIS:
✅ DO:
❌ NEVER SAY THESE PHRASES:
❌ FORBIDDEN BEHAVIORS:
The Skill provides a Python function summarize_csv(file_path) that:
"Here's sales_data.csv. Can you summarize this file?""Analyze this customer data CSV and show me trends."
"What insights can you find in orders.csv?"Dataset Overview
Summary Statistics
Insights
(Attached: trend plot)
analyze.py - Core analysis logicrequirements.txt - Python dependenciesresources/sample.csv - Example dataset for testingresources/README.md - Additional documentation~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.