Trust Assessment
web-search received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Command Injection via unsanitized query parameter.
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 | |
|---|---|---|---|---|
| CRITICAL | Command Injection via unsanitized query parameter The `web_search` command directly interpolates the `{{query}}` parameter into a `curl` shell command without proper sanitization or escaping. An attacker can inject shell metacharacters (e.g., `&`, `|`, `;`, `$()`, `` ` ``) into the `query` to execute arbitrary commands on the host system where the skill is run. This allows for remote code execution. Implement robust sanitization and shell escaping for the `query` parameter before it is used in the `curl` command. If possible, avoid direct shell execution with user-controlled input. Instead, use a dedicated HTTP client library in a programming language that handles URL encoding and command construction safely, or ensure the `query` is strictly validated and encoded for both URL and shell contexts. | LLM | SKILL.md:4 |
Scan History
Embed Code
[](https://skillshield.io/report/35a8f6b2c6f6c901)
Powered by SkillShield