Trust Assessment
my-play-music-from-yt received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Broad playwright-cli permissions allow arbitrary browser actions and JavaScript execution.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad playwright-cli permissions allow arbitrary browser actions and JavaScript execution The skill declares `Bash(playwright-cli:*)` as an allowed tool in its manifest, granting the LLM permission to execute `playwright-cli` with any arguments. `playwright-cli` is a powerful browser automation tool that can navigate to arbitrary URLs, interact with web pages, and execute arbitrary JavaScript within the browser context via its `eval` command. The skill explicitly demonstrates the use of `playwright-cli eval`. This broad permission, combined with the `eval` capability, could be exploited by a malicious prompt to perform actions like navigating to phishing sites, exfiltrating browser-accessible data (e.g., cookies, local storage) from legitimate sites, or executing malicious JavaScript on behalf of the user. The `--persistent` flag also means sensitive browser profile data (including login states) is stored on disk, which could be accessed if the `playwright-cli` session or its data directories are compromised. Restrict `playwright-cli` arguments to a safe allowlist of commands and patterns. If `eval` is necessary, implement strict sanitization and validation of the JavaScript code to be executed. Consider disallowing `--persistent` for sensitive operations or encrypting the persistent profile. Review the necessity of `Bash(playwright-cli:*)` and narrow it down to specific commands or argument patterns if possible. | LLM | SKILL.md:169 |
Scan History
Embed Code
[](https://skillshield.io/report/21d11ee52ccff8d1)
Powered by SkillShield