Trust Assessment
yt-video-downloader 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 Potential Command Injection via unsanitized yt-dlp arguments, Risk of credential exposure via --cookies-from-browser option.
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 | Potential Command Injection via unsanitized yt-dlp arguments The skill provides examples for executing `yt-dlp` commands, which are shell commands. If an AI agent directly interpolates user-provided input (e.g., `VIDEO_URL`, `PLAYLIST_URL`, or output paths in `-o`) into these commands without proper sanitization or escaping, it could lead to command injection. An attacker could craft a malicious URL or output path to execute arbitrary shell commands on the host system. The AI agent implementing this skill must rigorously sanitize and escape all user-provided inputs before constructing and executing `yt-dlp` commands. Specifically, ensure that `VIDEO_URL`, `PLAYLIST_URL`, and any custom output path arguments are properly quoted and escaped to prevent shell metacharacter interpretation. Consider using a library or function designed for safe shell command execution. | LLM | SKILL.md:20 | |
| MEDIUM | Risk of credential exposure via --cookies-from-browser option The skill notes that `yt-dlp` can use the `--cookies-from-browser chrome` option to access authenticated content. While a legitimate feature of `yt-dlp`, if an AI agent is prompted to use this option with a `VIDEO_URL` controlled by an attacker, it could potentially expose sensitive browser cookies to a malicious server or facilitate unauthorized access to user accounts if the downloaded content itself is malicious or redirects to an attacker-controlled domain. The agent must be extremely cautious when using this option with untrusted URLs. The AI agent should only use the `--cookies-from-browser` option with trusted and verified `VIDEO_URL`s. Implement strict validation and user confirmation before enabling this option, especially when the `VIDEO_URL` is derived from untrusted input. Consider sandboxing the execution environment or restricting access to browser profiles. | LLM | SKILL.md:128 |
Scan History
Embed Code
[](https://skillshield.io/report/9ed0fe1775753480)
Powered by SkillShield