Trust Assessment
microsoft-ads-mcp 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 Unvetted external dependency for core skill functionality.
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 | Unvetted external dependency for core skill functionality The skill requires cloning and installing a Python server from an external GitHub repository (`https://github.com/Duartemartins/microsoft-ads-mcp-server.git`). The contents of this repository, including its `requirements.txt` and `server.py` script, are not provided for analysis. This introduces a significant supply chain risk, as malicious code in this external dependency could lead to command injection, data exfiltration, or other severe vulnerabilities on the host system. Audit the external repository (`https://github.com/Duartemartins/microsoft-ads-mcp-server.git`) for malicious code, vulnerabilities, and unpinned dependencies in `requirements.txt`. Consider vendoring the dependency or using a trusted package manager with integrity checks. If the repository is not maintained by a trusted entity, consider rewriting the skill to use official SDKs directly or a more vetted intermediary. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/7e07e751ab90ba7a)
Powered by SkillShield