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 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Execution of Unverified External Script for macOS Agent Installation, Download of Unverified Executable for Windows Agent Installation.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 Findings3
| 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-bzrvt/SKILL.md:10 | |
| CRITICAL | Execution of Unverified External Script for macOS Agent Installation The skill instructs macOS users to obtain and execute an unverified script from `glot.io` by pasting it into their terminal. `glot.io` is a public pastebin-like service, and scripts hosted there can be modified, contain malicious code, or be removed without warning. This practice introduces a severe command injection and supply chain risk, as users are prompted to run arbitrary code from an untrusted and volatile source, potentially leading to system compromise or data exfiltration. 1. Remove reliance on external scripts from untrusted sources like pastebins. 2. If `openclaw-agent` is essential, provide a verifiable, signed binary or a script hosted within a trusted, version-controlled repository (e.g., a specific commit/tag on GitHub) with clear instructions for integrity verification (e.g., checksums). 3. Alternatively, integrate the agent's functionality directly into the skill or provide a more secure, auditable installation method. | LLM | SKILL.md:12 | |
| HIGH | Download of Unverified Executable for Windows Agent Installation The skill instructs Windows users to download an executable (`openclaw-agent.zip`) from a specific GitHub user's release page (`hedefbari`). While GitHub releases are generally more reliable than pastebins, downloading executables from individual user accounts without further verification (e.g., code signing, checksums, or a clear audit trail) introduces a significant supply chain risk. The use of a generic `latest` tag means the content could change without explicit versioning, and the password `openclaw` for archive extraction is suspicious and could indicate an attempt to obscure content or is simply poor security practice. 1. Provide a verifiable and signed executable for `openclaw-agent`. 2. Host the executable within an official, trusted organization's repository. 3. Specify a fixed version/tag instead of `latest` and provide checksums for integrity verification. 4. Avoid using passwords for archive extraction, or if necessary, explain its purpose and ensure it does not introduce a security vulnerability. | LLM | SKILL.md:9 |
Scan History
Embed Code
[](https://skillshield.io/report/57995d079c6e8310)
Powered by SkillShield