Trust Assessment
transak received a trust score of 65/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection in 'Get Order Status' via ORDER_ID, Command Injection in 'verify_webhook' function via payload.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 12, 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 | Command Injection in 'verify_webhook' function via payload The `payload` argument, which is expected to be untrusted user input from a webhook, is directly passed to `echo -n "$payload"` without proper sanitization. This allows an attacker to inject shell metacharacters (e.g., `$(evil_command)`) into the `payload` to execute arbitrary commands on the host system, as `echo`'s output is piped to `openssl`. This vulnerability is critical as it affects a security-sensitive webhook verification function. Ensure the `payload` variable is properly quoted or sanitized before being passed to `echo` and subsequently `openssl`. A more robust solution would be to use a dedicated HMAC function in a scripting language (e.g., Python's `hmac` module) that does not involve shell execution of user-controlled data. If shell execution is unavoidable, use `printf %s "$payload"` instead of `echo -n "$payload"` and ensure all shell metacharacters are escaped. | LLM | SKILL.md:175 | |
| HIGH | Command Injection in 'Get Order Status' via ORDER_ID The `ORDER_ID` variable, which is expected to be user-controlled, is directly interpolated into the `curl` command's URL path without proper sanitization. An attacker could inject shell metacharacters (e.g., `$(evil_command)` or `; evil_command`) into `ORDER_ID` to execute arbitrary commands on the host system when the `curl` command is executed. Sanitize `ORDER_ID` to ensure it only contains valid characters for an order ID (e.g., alphanumeric, hyphens). If `ORDER_ID` must contain special characters, ensure it is properly URL-encoded and shell-quoted before being used in the `curl` command. A safer approach would be to use a programming language's HTTP client library that handles URL construction and parameter encoding securely, rather than relying on shell execution with string interpolation. | LLM | SKILL.md:99 |
Scan History
Embed Code
[](https://skillshield.io/report/18d9e2c3804b7460)
Powered by SkillShield