Pandas Construction Analysis

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: pandas-construction-analysis Version: 2.1.0 This skill is classified as benign. It provides a comprehensive Pandas toolkit for construction data analysis, which inherently requires file system access for reading and writing data (CSV, Excel). The `claw.json` file explicitly requests `filesystem` permissions, which is justified by the skill's stated purpose and the code examples in `SKILL.md` (e.g., `pd.read_excel`, `df.to_csv`, `df.to_excel`). There is no evidence of malicious intent, such as data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection attempts in `SKILL.md` or `instructions.md` that would manipulate the AI agent to perform harmful actions.

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 may read or write local project data files as part of analysis and reporting.

Why it was flagged

The skill declares filesystem permission, which is expected for reading construction datasets and exporting reports, but it still gives the agent local file access.

Skill content
"permissions": [
    "filesystem"
  ]
Recommendation

Use explicit file paths, keep outputs in a known project folder, and review any export destination before allowing writes.

What this means

Analysis may involve running local Python code against files the user provides.

Why it was flagged

The skill provides Python/Pandas code patterns for local data processing. This is central to the stated purpose and is not shown as hidden or automatic install-time execution.

Skill content
import pandas as pd

# Read construction data
df = pd.read_excel("bim_export.xlsx")
Recommendation

Run analysis only on trusted datasets and avoid treating arbitrary user-supplied text as executable Python code.