Security Audit
lawvable/awesome-legal-skills:skills/docx-processing-openai
github.com/lawvable/awesome-legal-skillsTrust Assessment
lawvable/awesome-legal-skills:skills/docx-processing-openai received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 2 critical, 3 high, 1 medium, and 1 low severity. Key findings include Unsafe environment variable passthrough, Arbitrary command execution, Credential harvesting.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 25/100, indicating areas for improvement.
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 Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/docx-processing-openai/scripts/render_docx.py:103 | |
| CRITICAL | Credential harvesting Bulk environment variable dump Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/docx-processing-openai/scripts/render_docx.py:108 | |
| HIGH | Unsafe environment variable passthrough Bulk environment variable harvesting Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/docx-processing-openai/scripts/render_docx.py:108 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_cmd_no_check'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/docx-processing-openai/scripts/render_docx.py:103 | |
| HIGH | Arbitrary file write via user-controlled output directory The `scripts/render_docx.py` script allows a user to specify an arbitrary `--output_dir` for rendered images. The script then uses `os.makedirs` and `image.save` (implied by the function's purpose and visible `makedirs` call) to write files into this directory. A malicious actor could specify a sensitive system directory (e.g., `/etc`, `/root/.ssh`, `/var/www/html`) to attempt to write or overwrite files. If the agent has sufficient permissions, this could lead to privilege escalation, denial of service, or unauthorized data modification. Restrict the `output_dir` to a dedicated, sandboxed directory within the agent's workspace (e.g., `tmp/output/` or a subdirectory of the current working directory that is explicitly managed by the agent). Validate and sanitize the `output_dir` path to prevent directory traversal (`..`) or absolute paths outside the allowed sandbox. | LLM | scripts/render_docx.py:120 | |
| MEDIUM | Unpinned Python dependencies The `SKILL.md` provides installation instructions for Python packages (`python-docx`, `pdf2image`) without specifying exact versions. This practice, known as unpinned dependencies, can lead to supply chain vulnerabilities. If a future version of these packages introduces a security flaw, breaking change, or even malicious code, the skill would automatically install it, potentially compromising the agent's environment. Pin all Python dependencies to exact versions (e.g., `python-docx==0.8.11 pdf2image==1.16.0`). Use a `requirements.txt` or `pyproject.toml` with locked dependencies. Regularly review and update pinned versions to incorporate security patches. | LLM | SKILL.md:40 | |
| LOW | Environment variables passed to external processes The `run_cmd_no_check` function, used for executing `soffice` and `pdftoppm`, passes a copy of the current environment variables (`env=os.environ.copy()`) to these external processes. If the agent's environment contains sensitive information (e.g., API keys, cloud credentials, tokens), these could be exposed to the executed processes. While `soffice` and `pdftoppm` are generally trusted tools, a vulnerability or compromise in these tools could theoretically lead to the exfiltration of these environment variables. Explicitly filter or clear environment variables passed to external processes, providing only those strictly necessary for the command to function. For example, use `env={}` or `env={'PATH': os.environ.get('PATH')}`. | LLM | scripts/render_docx.py:99 |
Scan History
Embed Code
[](https://skillshield.io/report/c3ff2664fe2d627e)
Powered by SkillShield