Trust Assessment
imagerouter 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 and Data Exfiltration via Unsanitized File Paths in `curl` Uploads.
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 14, 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 and Data Exfiltration via Unsanitized File Paths in `curl` Uploads The skill's documentation demonstrates `curl` commands for uploading local files using the `-F 'name=@filename'` syntax (e.g., `image[]=@/path/to/your/image.webp`). If the skill allows users to specify arbitrary file paths for `image[]` or `mask[]` parameters without proper sanitization or validation, a malicious user could inject shell commands (e.g., `image[]=@$(rm -rf /)`) or upload sensitive system files (e.g., `image[]=@/etc/passwd`) to the ImageRouter API. This could lead to command injection (executing arbitrary commands on the host system) or data exfiltration (leaking local files). The skill implementation must strictly validate and sanitize any user-provided file paths before incorporating them into `curl` commands. This includes checking for path traversal attempts (e.g., `../`), shell metacharacters, and ensuring files are within an allowed directory or are explicitly selected by the user through a secure file picker. Robust shell argument escaping should be applied to all user-controlled inputs used in shell commands. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/ff72263cf5b1dd71)
Powered by SkillShield