Trust Assessment
whatsapp-business 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 Environment 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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Environment Variable Interpolation The skill's example `curl` commands directly interpolate environment variables (`$WHATSAPP_PHONE_ID`, `$WHATSAPP_TOKEN`) into a shell command string. If these environment variables contain malicious shell metacharacters or commands (e.g., through a compromised environment or untrusted input used to set them), they could lead to arbitrary command execution on the host system. This is a classic command injection vulnerability, as the shell will interpret and execute any valid commands embedded within the variable's value. Avoid direct interpolation of potentially untrusted variables into shell commands. Instead, use a dedicated HTTP client library in a programming language (e.g., Python's `requests` or Node.js's `axios`) to construct and send API requests programmatically. This approach avoids shell execution entirely. If shell execution is unavoidable, ensure all variables are rigorously sanitized and properly escaped for the shell context (e.g., using `printf %q` in bash) to prevent injection of shell metacharacters. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/4c5e7bbfc67e279f)
Powered by SkillShield