Trust Assessment
office-mcp received a trust score of 82/100, 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 Unvalidated output path allows arbitrary file writes, Unpinned dependencies in installation instructions.
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 12, 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 | Unvalidated output path allows arbitrary file writes The `create_docx` and `create_xlsx` tools accept an `output_path` parameter directly from user input. This path is then used without validation in `doc.save(output_path)` and `wb.save(output_path)`. An attacker could exploit this to write files to arbitrary locations on the filesystem (e.g., `/etc/passwd`, `/var/www/html/malicious.php`), leading to data corruption, system compromise, or data exfiltration if a public path is specified. This directly leverages the declared `file_operations` permission in an insecure manner. Implement strict validation and sanitization for `output_path`. Restrict file writes to a designated, sandboxed directory. Do not allow absolute paths or paths containing `..` to be specified by the user. Consider using a temporary file system or a dedicated output directory for all generated files. | LLM | SKILL.md:50 | |
| MEDIUM | Unpinned dependencies in installation instructions The `Installation` section lists Python dependencies (`python-docx`, `openpyxl`, `python-pptx`, `reportlab`, `jinja2`) without specifying exact versions. This can lead to non-deterministic builds, introduce unexpected breaking changes, or pull in versions with known security vulnerabilities. It also increases the risk of dependency confusion attacks if a malicious package with the same name is published. Pin all dependencies to specific, known-good versions (e.g., `python-docx==0.8.11`). Use a `requirements.txt` file with exact versions to ensure consistent and secure deployments. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/078bb44de11f05d1)
Powered by SkillShield