Trust Assessment
intodns received a trust score of 88/100, 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 User-Controlled Domain in `curl` commands.
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 User-Controlled Domain in `curl` commands The skill instructs the LLM to 'Execute a quick scan' and provides `curl` commands within `bash` code blocks. The `DOMAIN` parameter in these `curl` commands is directly derived from user input. If the LLM's execution environment allows direct shell command execution based on these instructions, a malicious user could inject arbitrary shell commands by providing a specially crafted `DOMAIN` (e.g., `example.com; rm -rf /`). The skill's sanitization step only handles URL formatting, not robust shell escaping, leaving a potential vulnerability for command injection. 1. Clarify that `curl` examples are illustrative of API calls, not literal shell commands to be executed by the LLM. 2. If shell execution is intended, implement robust shell escaping for the user-controlled `DOMAIN` parameter before constructing the `curl` command. 3. Prefer using a dedicated API client library (e.g., Python `requests`) which handles URL encoding automatically, rather than constructing shell commands directly. | LLM | SKILL.md:27 |
Scan History
Embed Code
[](https://skillshield.io/report/b0dfef4fc07aaefe)
Powered by SkillShield