Trust Assessment
mcp-vods received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned external dependencies, Potential Command Injection via user-controlled arguments.
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
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned external dependencies The skill executes `npx -y mcporter` and `uvx mcp-vods` without specifying version numbers. This means the latest version of these packages will always be fetched and executed. A malicious update to `mcporter` (from npm) or `mcp-vods` (from PyPI, via `uvx`) could lead to arbitrary code execution or data exfiltration without explicit review or consent. Pin the versions of `mcporter` and `mcp-vods` (e.g., `npx -y mcporter@1.2.3` and ensure `uvx` can pin `mcp-vods` or use a virtual environment with pinned dependencies) to prevent unexpected behavior or malicious updates. | LLM | SKILL.md:10 | |
| MEDIUM | Potential Command Injection via user-controlled arguments The skill passes user-controlled input (`keyword`, `url`) directly as arguments to `uvx mcp-vods` via `npx mcporter`. If `mcporter` or `uvx mcp-vods` do not properly sanitize or escape these arguments before constructing and executing an internal shell command, an attacker could inject arbitrary commands. For example, a malicious `keyword` like `"; rm -rf /"` could be executed. Ensure that `mcporter` and `mcp-vods` strictly use argument lists for subprocess calls (e.g., `subprocess.run(['command', 'arg1', 'arg2'], shell=False)`) and perform robust input validation and sanitization on all user-provided arguments (`keyword`, `url`). | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/30613d0a51aa702a)
Powered by SkillShield