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: 2 critical, 1 high, 0 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, External script execution for openclaw-agent installation (macOS), Untrusted executable download for openclaw-agent (Windows).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 53/100, 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-saosh/SKILL.md:10 | |
| CRITICAL | External script execution for openclaw-agent installation (macOS) The skill instructs macOS users to copy and paste an installation script from an external snippet hosting service (glot.io) directly into their Terminal. This is a direct instruction to execute arbitrary, unvetted code from an untrusted external source, posing a severe supply chain risk and a potential command injection vulnerability for the user. The content of the script is not provided or vetted within the skill package, making it impossible to ascertain its safety. Remove instructions to execute unvetted external scripts. If 'openclaw-agent' is a required prerequisite, it should be distributed securely, ideally as part of the skill package or from a trusted, verifiable source with clear installation instructions that do not involve arbitrary script execution. | LLM | SKILL.md:10 | |
| HIGH | Untrusted executable download for openclaw-agent (Windows) The skill instructs Windows users to download an executable ('openclaw-agent.zip') from a specific GitHub release page and extract it using a hardcoded password ('openclaw'). Downloading and running executables from external, potentially unverified GitHub user repositories, especially with a hardcoded password, introduces a significant supply chain risk. The executable's contents and behavior are not vetted within the skill package, and the use of a hardcoded password for extraction is suspicious. Distribute 'openclaw-agent' securely, ideally as part of the skill package or from a trusted, verifiable source. Avoid instructing users to download and run executables from arbitrary URLs, especially with hardcoded passwords, without proper verification. | LLM | SKILL.md:7 | |
| LOW | Unpinned 'yfinance' dependency The 'yfinance' package is specified in the manifest without a version pin. This means that the latest version available at installation time will be used, which could introduce breaking changes or new vulnerabilities if a malicious or buggy update is pushed to the package repository. While 'yfinance' is a widely used package, unpinned dependencies are a general supply chain risk. Pin the 'yfinance' dependency to a specific, known-good version (e.g., "package": "yfinance==0.2.28") to ensure consistent and secure installations. | LLM | Manifest (frontmatter JSON) |
Scan History
Embed Code
[](https://skillshield.io/report/a86aad163842b9ff)
Powered by SkillShield