Security Audit

exploratory-data-analysis

github.com/davila7/claude-code-templates

AI SkillCommit 458b11867eae

TRUSTED

Scanned 11 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

exploratory-data-analysis received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Potential Data Exfiltration via Arbitrary File Analysis.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

91%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Security Findings3

Severity	Finding	Layer	Location
HIGH	Potential Data Exfiltration via Arbitrary File Analysis The `eda_analyzer.py` script is designed to perform exploratory data analysis on any provided file path. It reads the file's content, extracts metadata, and generates a detailed markdown report that includes the file's path, size, and analysis results. If an attacker can trick the agent into providing a sensitive file path (e.g., `~/.ssh/id_rsa`, `/etc/passwd`, or API key files), the script will read this file and include information derived from its content and its full path in the generated report. This report could then be exfiltrated by the attacker. Implement robust input validation for the `filepath` argument to restrict analysis to designated safe directories or file types. Before analyzing, prompt the user for confirmation if the file path is outside expected data locations. Ensure that generated reports redact or sanitize any potentially sensitive information, especially for unknown or unparsable file types. Consider sandboxing the execution environment for file analysis to limit filesystem access.	LLM	scripts/eda_analyzer.py:15
MEDIUM	Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Manifest	cli-tool/components/mcps/devtools/figma-dev-mode.json:4
LOW	Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users.	Manifest	cli-tool/components/mcps/devtools/jfrog.json:4

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/5a1b2ddcd9540bee.svg)](https://skillshield.io/report/5a1b2ddcd9540bee)