Trust Assessment
searxng 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 Command Injection via 'YOUR_QUERY' placeholder.
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 Command Injection via 'YOUR_QUERY' placeholder The skill's documentation provides `curl` command examples where the `YOUR_QUERY` placeholder is directly embedded within a double-quoted string in a shell command. If the LLM substitutes user-controlled input into `YOUR_QUERY` without proper shell escaping, an attacker could inject arbitrary shell commands. For example, injecting `" && malicious_command #` into `YOUR_QUERY` could break out of the URL string and execute `malicious_command`. The LLM must ensure that any user-provided input for `YOUR_QUERY` is thoroughly shell-escaped before being inserted into the `curl` command. This prevents malicious characters from being interpreted as shell commands. A safer approach would be to use a programming language's HTTP client library that handles URL encoding and command construction securely, rather than directly concatenating strings into shell commands. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/76af7573fa50ede7)
Powered by SkillShield