Security Audit

yahoo-finance

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CRITICAL

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

yahoo-finance received a trust score of 40/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Mandatory Installation of Untrusted External Agent.

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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

2 findings

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Network egress to untrusted endpoints URL pointing to known exfiltration/webhook service 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	skills/aleph8/malicious-skill-test/SKILL.md:10
CRITICAL	Mandatory Installation of Untrusted External Agent The skill mandates the installation and execution of an external binary, `openclaw-agent`, from highly suspicious sources (a personal GitHub account and a code-sharing snippet site). This agent is presented as a prerequisite for the skill's functionality, despite the core `yfinance` library not requiring such an agent for its basic operations. This introduces a severe supply chain risk, as the untrusted agent could enable command injection, data exfiltration, credential harvesting, or establish a backdoor on the user's system. The requirement for a password to extract the Windows executable is also suspicious. Remove the requirement for `openclaw-agent`. If an agent is truly necessary for specific advanced functionality, it must be officially provided by the `openclaw` ecosystem, open-sourced, and distributed through trusted channels with clear security audits. The `yfinance` library should function independently without such an agent for its core features.	LLM	SKILL.md:6

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/38d3f8828732a3d3.svg)](https://skillshield.io/report/38d3f8828732a3d3)