Security Audit
lawvable/awesome-legal-skills:skills/outlook-emails-lawvable
github.com/lawvable/awesome-legal-skillsTrust Assessment
lawvable/awesome-legal-skills:skills/outlook-emails-lawvable received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Suspicious import: requests, Unpinned dependencies, Default Azure Client ID points to third-party application.
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 26, 2026 (commit 4d82d4cf). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Suspicious import: requests Import of 'requests' 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/outlook-emails-lawvable/scripts/outlook_oauth.py:30 | |
| MEDIUM | Unpinned dependencies The skill's dependencies (`msal`, `requests`, `python-dotenv`) are not pinned to specific versions. This can lead to unexpected behavior, security vulnerabilities, or supply chain attacks if a new version of a dependency introduces malicious code or breaking changes. It makes the build non-deterministic. Pin all dependencies to exact versions (e.g., `msal==1.20.0`, `requests==2.31.0`, `python-dotenv==1.0.0`). | Static | scripts/outlook_oauth.py:3 | |
| INFO | Default Azure Client ID points to third-party application The skill uses a default `AZURE_CLIENT_ID` (`ebaa3d3e-7da3-46ea-8845-c7db6dbae8f0`) which is identified as a 'Lawvable shared app'. Users authenticate against this third-party application. While the skill explicitly states it's read-only and has zero data retention, users should be aware they are granting permissions to an application controlled by Lawvable, not directly to their own local environment. This is a trust consideration, not a direct code vulnerability, especially since the requested scopes are limited to `User.Read` and `Mail.Read`. Users can override this by setting their own `AZURE_CLIENT_ID` environment variable, as described in the `SKILL.md`. For the skill developer, consider making the use of a custom client ID more prominent or providing a clear warning about the trust implications of using a shared client ID. | Static | scripts/outlook_oauth.py:26 |
Scan History
Embed Code
[](https://skillshield.io/report/518c9e36da7b2b3d)
Powered by SkillShield