Trust Assessment
modelready received a trust score of 63/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Arbitrary command injection via 'extra' parameter.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command injection via 'extra' parameter The `start` command allows an `extra` parameter to pass additional arguments to the `vllm.entrypoints.openai.api_server` Python script. However, the value of `EXTRA` is expanded unquoted into an array (`EXTRA_ARR=($EXTRA)`), which allows arbitrary shell commands to be injected and executed before the `python3` command. An attacker can craft the `extra` parameter to include shell metacharacters (e.g., `;`, `|`, `&`, `$(...)`) to execute malicious commands on the host system. The `EXTRA` variable should not be expanded unquoted. If the intent is to pass multiple arguments, a safer parsing mechanism is required that does not involve shell interpretation of user input. For example, the skill could define specific parameters for common `vLLM` options instead of a generic `extra` passthrough. If a generic passthrough is unavoidable, consider passing the entire `EXTRA` string as a single argument to the Python script and let the Python script handle the parsing of `vLLM` specific arguments, or implement strict input validation to disallow shell metacharacters. | LLM | tool/modelready.sh:173 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/carol-gutianle/modelready/tool/modelready.sh:17 |
Scan History
Embed Code
[](https://skillshield.io/report/25a92e23b742510f)
Powered by SkillShield