Trust Assessment
weex-trading received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Suspicious import: requests, Shell Command Injection via Unsanitized Variable Interpolation.
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 | |
|---|---|---|---|---|
| HIGH | Shell Command Injection via Unsanitized Variable Interpolation The skill's shell command examples construct API request paths and JSON bodies by directly interpolating variables (e.g., SYMBOL, COIN, ORDER_ID, LEVERAGE) into strings. If these variables contain user-controlled input with shell metacharacters (e.g., `$(command)` or `"$(command)"`), they could lead to arbitrary command execution. This affects both the `generate_signature` function (where `path` and `body` are interpolated into `message` for `echo`) and the `curl -d` commands (where JSON `BODY` is constructed via string concatenation). The Python client script `scripts/weex_client.py` correctly uses `json.dumps` and `urlencode` to prevent this, but the shell examples in `SKILL.md` do not. When constructing shell commands with variable input, ensure all variables are properly sanitized or escaped. For shell arguments, use `printf %q` or similar escaping mechanisms. For JSON bodies, use a dedicated JSON processing tool like `jq` to construct the JSON object safely, or ensure that all interpolated values are strictly validated and escaped to prevent breaking out of string literals. For URL parameters, use a URL encoding utility. The Python client script `scripts/weex_client.py` demonstrates a safer approach using `json.dumps` and `urllib.parse.urlencode`. | LLM | SKILL.md:30 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/bowen31337/weex-trading-skills/scripts/weex_client.py:44 |
Scan History
Embed Code
[](https://skillshield.io/report/952feb25c7669b5d)
Powered by SkillShield