Intelligent data analysis report generator

AdvisoryAudited by Static analysis on May 13, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent will run local Python commands and read the spreadsheet files the user provides.

Why it was flagged

The skill asks the agent to execute local Python tools against a user-selected spreadsheet and write outputs. This is central to the skill's purpose, but users should understand local command execution is part of the workflow.

Skill content
Run `analyzer.py` on the file → get `analysis.json`
Run `chart_generator.py` with analysis + style → get `charts.json`
Recommendation

Use the skill only on files you intend to analyze, keep outputs in the workspace, and review any optional custom analysis code before running it.

What this means

Installing dependencies or opening the generated report may fetch code from external package/CDN providers.

Why it was flagged

The skill depends on external Python packages and a third-party CDN script. This is disclosed and purpose-aligned, but package versions/hashes and CDN integrity are not specified.

Skill content
ECharts 5.5.0 (loaded via CDN in the HTML template — no local install needed)

If dependencies missing, install: `pip install pandas openpyxl numpy`
Recommendation

Prefer a virtual environment, pin package versions, and consider bundling ECharts locally or adding Subresource Integrity for the CDN script.

ConcernHigh Confidence
ASI05: Unexpected Code Execution
What this means

A booby-trapped CSV or Excel file could make the generated HTML report run unwanted JavaScript in the browser, potentially altering the report or sending embedded report data over the network.

Why it was flagged

The generated report builds HTML and JavaScript from embedded chart data, inserts it with innerHTML, and then evals the assembled script. Because chart IDs, titles, and metric names can be derived from spreadsheet columns, a malicious or untrusted file could cause JavaScript execution when the report is opened.

Skill content
const entries = Object.entries(CHART_DATA); ... const cid = 'chart_' + id; ... sectionContainer.innerHTML = html; ... eval(chartInitCode);
Recommendation

Remove eval, initialize charts directly in a loop, generate safe fixed element IDs, escape or use textContent for all data-derived text, and safely serialize JSON embedded inside script tags.