Trust Assessment
umami-stats received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Credential Exfiltration via User-Controlled Base URL.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Credential Exfiltration via User-Controlled Base URL The `scripts/umami_query.py` script allows the `--base-url` argument to be set by the user. If an untrusted prompt can manipulate this argument, the `UMAMI_API_KEY` (read from environment variables) will be sent in the HTTP headers to an arbitrary, potentially malicious, server. This constitutes a direct credential harvesting and data exfiltration risk, as the API key is used for authentication to the user-specified base URL. Implement an allowlist for the `--base-url` argument within the `umami_query.py` script, restricting it to known, trusted Umami API endpoints (e.g., `https://api.umami.is` and explicitly configured self-hosted instances). Alternatively, ensure that the agent orchestrating the skill strictly sanitizes or disallows untrusted input from controlling the `--base-url` parameter. Consider using a dedicated API key for the skill that is scoped to specific domains or IPs if the Umami API supports it. | LLM | scripts/umami_query.py:169 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/hfichter/umami-stats/scripts/umami_query.py:18 |
Scan History
Embed Code
[](https://skillshield.io/report/76c1a67bd05f3bce)
Powered by SkillShield