Trust Assessment
spacex 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 unsanitized 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 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 unsanitized arguments The skill describes a CLI interface (`spacex`) that accepts user-controlled arguments such as `[limit]` and `<id>`. These arguments are passed to an underlying shell script (`{skill_folder}/spacex`), as indicated by the 'Script location' and the `bins` requirement in the manifest. If the script does not properly sanitize or escape these inputs before using them in shell commands, an attacker could inject arbitrary shell commands. For example, providing `1; rm -rf /` as a `limit` or `5eb87d47ffd86e000604b38a; evil_command` as an `id` could lead to critical system compromise. The underlying `spacex` script must rigorously sanitize and escape all user-provided arguments (e.g., `limit`, `id`) before incorporating them into any shell command. This typically involves using `printf %q` in bash or similar robust escaping mechanisms, or strictly validating input types (e.g., ensuring `limit` is an integer) to prevent shell metacharacters from being interpreted as commands. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/2fcc44622bd5313d)
Powered by SkillShield