Security Audit
lawvable/awesome-legal-skills:skills/docx-processing-superdoc
github.com/lawvable/awesome-legal-skillsTrust Assessment
lawvable/awesome-legal-skills:skills/docx-processing-superdoc received a trust score of 48/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned dependency in `npx` command, Potential for command injection via user-controlled arguments, Broad filesystem access for document processing.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 48/100, 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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unpinned dependency in `npx` command The skill uses `npx @superdoc-dev/cli@latest` to execute a command-line tool. Using `@latest` means that the agent will always fetch and execute the most recent version of the package from npm. This introduces a critical supply chain risk, as a malicious actor could publish a compromised version of the package, which would then be automatically executed by the agent without any review or version pinning. This could lead to arbitrary code execution or data exfiltration. Pin the dependency to a specific, known-good version (e.g., `npx @superdoc-dev/cli@1.2.3`) to ensure deterministic and secure execution. Regularly review and update the pinned version to mitigate known vulnerabilities. | Static | SKILL.md:10 | |
| HIGH | Potential for command injection via user-controlled arguments The skill defines commands that execute `npx @superdoc-dev/cli` with arguments like `<pattern>`, `<files...>`, `<find>`, and `<to>`. These arguments are expected to be derived from untrusted user input. If the LLM constructs the shell command by directly interpolating user input without proper sanitization or escaping, a malicious user could inject arbitrary shell commands (e.g., by providing a filename like `'; rm -rf /;'`). This could lead to arbitrary code execution on the host system. The LLM implementation responsible for invoking this skill must rigorously sanitize and escape all user-provided arguments before constructing and executing the shell command. Consider using a safe command execution library that handles argument escaping automatically. | Static | SKILL.md:10 | |
| MEDIUM | Broad filesystem access for document processing The skill allows searching, replacing, and reading `.docx` files using glob patterns like `./**/*.docx`. This grants the underlying `npx` process broad recursive access to the filesystem, potentially allowing it to read or modify any `.docx` file on the system. While this might be intended functionality for document processing, it represents a significant permission scope. If combined with command injection, this could be exploited to access or modify sensitive files outside the intended scope. Implement strict access controls or sandboxing for the execution environment to limit the filesystem scope accessible to the `npx` command. If possible, restrict file access to specific, user-designated directories only. | Static | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/13f16f8a834555b6)
Powered by SkillShield