Trust Assessment
model-router-premium 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 Arbitrary File Read via Path Traversal.
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 | Arbitrary File Read via Path Traversal The `scripts/router.py` skill takes a file path via the `--models` command-line argument and directly uses it to open and load a JSON file. If an LLM agent allows untrusted user input to control this argument, a malicious user could specify paths like `/etc/passwd` or `../../secrets.json` to read arbitrary files from the system, leading to data exfiltration. Implement strict input validation for the `--models` argument. Restrict file paths to a predefined, safe directory (e.g., a `models` subdirectory), sanitize path components, or ensure the LLM agent itself validates and sanitizes file paths before passing them to the skill. | LLM | scripts/router.py:26 |
Scan History
Embed Code
[](https://skillshield.io/report/38844f9435cb756b)
Powered by SkillShield