Trust Assessment
weather received a trust score of 88/100, 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 Command Injection via unsanitized user input in `curl` 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 18, 2026 (commit b62bd290). 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 Command Injection via unsanitized user input in `curl` arguments The skill's documentation (`SKILL.md`) provides examples of using `curl` to fetch weather data, where a location (e.g., 'London') is embedded directly into the URL. If the LLM is instructed to substitute user-provided input for this location without proper sanitization or shell escaping, a malicious user could inject arbitrary shell commands. For example, if a user provides input like `London$(id)` and the LLM constructs `curl "wttr.in/London$(id)?format=3"`, the `id` command would be executed on the host system. The `SKILL.md` does not provide any explicit guidance or examples for securely handling user input when constructing these shell commands, making the LLM prone to generating vulnerable commands. Instruct the LLM to always sanitize and shell-escape user-provided input before embedding it into `curl` commands. Specifically, ensure that any user-controlled string used as part of the URL path or query parameters is properly URL-encoded and then shell-quoted to prevent both URL-based and shell-based command injection. Consider providing explicit instructions or a helper function within the skill's documentation for safe input handling. | LLM | SKILL.md:29 |
Scan History
Embed Code
[](https://skillshield.io/report/c846eb68b5819b6e)
Powered by SkillShield