Trust Assessment
weather-checker received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Unvalidated user input allows URL parameter injection.
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 | |
|---|---|---|---|---|
| MEDIUM | Unvalidated user input allows URL parameter injection The `city` parameter is directly interpolated into the OpenWeatherMap API URL without sanitization or validation. This allows a malicious user to inject additional query parameters (e.g., `&units=imperial`) into the API request, overriding the skill's intended behavior (e.g., forcing imperial units instead of metric). This grants the user excessive control over the API request parameters, effectively broadening the permissions of the user to manipulate the external API call beyond the skill's design. Implement robust input validation and sanitization for the `city` parameter. Ensure that only the city name is passed to the `q` parameter, and other parameters like `units` and `appid` are controlled solely by the skill. Consider URL encoding the `city` parameter after validation to prevent injection of special characters. | LLM | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/a16f7ba928830542)
Powered by SkillShield