Trust Assessment
snow-report 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 Potential URL Injection via User-Controlled Slug in Browser Tool.
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 | Potential URL Injection via User-Controlled Slug in Browser Tool The skill uses a `browser` tool to navigate to URLs constructed with a `{slug}` parameter (e.g., `https://opensnow.com/location/{slug}/snow-summary`). This `{slug}` is derived from user input (resort names or SnowTick codes). The skill explicitly instructs users to 'grab slug from URL' for unlisted resorts, indicating direct user influence over this parameter. If the `browser` tool or the skill's logic does not strictly validate and sanitize the `{slug}` before constructing the `targetUrl`, a malicious user could potentially inject arbitrary URLs or URL schemes (e.g., `file://`, `data://`, `javascript://`). This could lead to Server-Side Request Forgery (SSRF) if the browser tool can access internal network resources, local file disclosure if `file://` schemes are supported, or navigation to malicious external websites, allowing the skill to access or exfiltrate data from unintended sources. Implement strict validation and sanitization of the `{slug}` parameter before it is used to construct the `targetUrl` for the `browser` tool. Ensure the `slug` only contains expected characters (e.g., alphanumeric, hyphens) and does not allow URL schemes, path traversal characters, or arbitrary domain names. Ideally, the `browser` tool itself should enforce a whitelist of allowed domains (e.g., `opensnow.com`) and URL patterns when invoked with user-controlled input. | LLM | SKILL.md:59 |
Scan History
Embed Code
[](https://skillshield.io/report/6f064638e6f72564)
Powered by SkillShield