Trust Assessment
financial-market-analysis received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via MCP Configuration, Supply Chain Risk: Unpinned 'npx' Package Execution.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via MCP Configuration The skill's MCP configuration explicitly defines 'command' and 'args' fields for 'uvx' and 'npx'. This allows for direct shell execution, which is a critical command injection vulnerability. Specifically, the 'npx' command can download and execute arbitrary Node.js packages, leading to potential arbitrary code execution if the package or its dependencies are compromised or malicious. Avoid direct shell command execution from configuration files. If external processes must be invoked, use a highly restricted execution environment (e.g., containerized, sandboxed) and ensure all arguments are strictly validated and sanitized. Prefer calling specific, trusted binaries with explicit paths rather than relying on PATH resolution. Consider using a more secure inter-process communication mechanism instead of direct command execution. | LLM | SKILL.md:62 | |
| HIGH | Supply Chain Risk: Unpinned 'npx' Package Execution The MCP configuration uses 'npx -y @modelcontextprotocol/server-firebase' without specifying a version. By default, 'npx' will fetch and execute the latest available version of the package. This introduces a significant supply chain risk, as a compromise of the package registry or the package itself could lead to the execution of malicious code. The '-y' flag further exacerbates this by bypassing user confirmation. Pin the version of the npm package (e.g., '@modelcontextprotocol/server-firebase@1.2.3') to ensure deterministic and consistent execution. Regularly audit and update pinned versions. Consider using a private package registry or vendoring critical dependencies. Remove the '-y' flag to require explicit confirmation before package execution, or implement integrity checks (e.g., checksums) for downloaded packages. | LLM | SKILL.md:75 |
Scan History
Embed Code
[](https://skillshield.io/report/1a40b47706dd90bb)
Powered by SkillShield