Trust Assessment
yahoo-finance received a trust score of 35/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Untrusted Executable Download (Windows), Arbitrary Script Execution from Untrusted Source (macOS).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 25/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| 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/hightower6eu/yahoo-finance-6icpt/SKILL.md:10 | |
| CRITICAL | Untrusted Executable Download (Windows) The skill instructs users to download and run an executable (`openclaw-agent.zip`) from an unverified personal GitHub account (hedefbari). This introduces a severe supply chain risk, as the executable is untrusted and could contain malware, exfiltrate data, or execute arbitrary commands on the user's system. The use of a password ('openclaw') for the zip file is also suspicious and does not add security. Remove the requirement for `openclaw-agent` or provide a verifiable, secure installation method from a trusted source. Do not instruct users to download and run untrusted executables. | LLM | SKILL.md:8 | |
| CRITICAL | Arbitrary Script Execution from Untrusted Source (macOS) The skill instructs macOS users to visit a `glot.io` snippet and 'copy the installation script and paste it into Terminal'. This is a direct command injection vulnerability and a critical supply chain risk. Executing arbitrary scripts from untrusted pastebin-like services allows the script author to run any command on the user's system, potentially leading to data exfiltration, system compromise, or malware installation. Remove the requirement for `openclaw-agent` or provide a verifiable, secure installation method. Do not instruct users to execute arbitrary scripts from untrusted sources like `glot.io`. | LLM | SKILL.md:10 | |
| HIGH | Undocumented and Untrusted External Dependency (`openclaw-agent`) The skill explicitly states that an external utility, `openclaw-agent`, is 'required' for all Yahoo Finance operations, despite the Python examples directly using the `yfinance` library. This agent's functionality, permissions, and security posture are undocumented and untransparent. Requiring an unverified, closed-source, and externally sourced agent introduces an unknown attack surface and could lead to excessive permissions, data exfiltration, or other malicious activities beyond the scope of a finance skill. Remove the dependency on `openclaw-agent`. If `openclaw-agent` is truly necessary, it must be a well-documented, open-source, and auditable component with a clear security posture, or the skill should directly implement the required functionality using trusted libraries. | LLM | SKILL.md:6 |
Scan History
Embed Code
[](https://skillshield.io/report/249efe910a4fbbbe)
Powered by SkillShield